c4f3dbed77
- Add OpenClaw launchd plist (gateway on port 8080) - Update Llama-3.3-70B Modelfile: fix FROM path, add tool-calling TEMPLATE, set num_ctx 32768 (fits 70B in 64GB with safe headroom) - Update Codestral-22B and Qwen3-32B Modelfiles - Add Modelfiles for all models in ~/Models/LLM and ~/Models/MLX: EVA-LLaMA-3.33-70B, Midnight-Miqu-70B, QwQ-32B, Qwen3.5-35B, Qwen3-Coder-30B, Qwen3-Coder-Next, Qwen3-VL-30B, GLM-4.6V-Flash, DeepSeek-R1-8B, gemma-3-27b, and MLX variants - Add import-local-models.sh helper script Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1978 lines
179 KiB
JSON
1978 lines
179 KiB
JSON
{
|
|
"metadata": {
|
|
"total_size": 31820755968,
|
|
"total_parameters": 29943393920
|
|
},
|
|
"weight_map": {
|
|
"lm_head.biases": "model-00007-of-00007.safetensors",
|
|
"lm_head.scales": "model-00007-of-00007.safetensors",
|
|
"lm_head.weight": "model-00007-of-00007.safetensors",
|
|
"model.embed_tokens.biases": "model-00001-of-00007.safetensors",
|
|
"model.embed_tokens.scales": "model-00001-of-00007.safetensors",
|
|
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.0.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.1.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.10.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.11.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.12.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.13.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.14.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.15.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.15.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.16.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.17.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.18.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.19.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.2.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.20.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.21.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.gate.e_score_correction_bias": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.gate.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.22.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.23.self_attn.embed_q.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.embed_q.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.embed_q.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.o_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.o_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_a_layernorm.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_a_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_a_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_a_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_b_proj.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_b_proj.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.q_b_proj.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.unembed_out.biases": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.unembed_out.scales": "model-00003-of-00007.safetensors",
|
|
"model.layers.23.self_attn.unembed_out.weight": "model-00003-of-00007.safetensors",
|
|
"model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.24.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.25.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.26.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.27.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.28.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.29.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.3.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.gate.e_score_correction_bias": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.gate.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.30.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.31.self_attn.embed_q.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.embed_q.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.embed_q.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.o_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.o_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_a_layernorm.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_a_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_a_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_a_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_b_proj.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_b_proj.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.q_b_proj.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.unembed_out.biases": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.unembed_out.scales": "model-00004-of-00007.safetensors",
|
|
"model.layers.31.self_attn.unembed_out.weight": "model-00004-of-00007.safetensors",
|
|
"model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.32.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.33.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.34.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.35.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.36.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.37.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.gate.e_score_correction_bias": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.gate.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.38.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.39.self_attn.embed_q.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.embed_q.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.embed_q.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.o_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.o_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_a_layernorm.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_a_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_a_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_a_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_b_proj.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_b_proj.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.q_b_proj.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.unembed_out.biases": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.unembed_out.scales": "model-00005-of-00007.safetensors",
|
|
"model.layers.39.self_attn.unembed_out.weight": "model-00005-of-00007.safetensors",
|
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.4.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.40.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.41.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.42.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.43.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.44.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.45.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.gate.e_score_correction_bias": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.gate.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.down_proj.biases": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.down_proj.scales": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.gate_proj.biases": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.gate_proj.scales": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.up_proj.biases": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.up_proj.scales": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
|
"model.layers.46.self_attn.embed_q.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.embed_q.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.embed_q.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.o_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.o_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_a_layernorm.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_a_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_a_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_a_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_b_proj.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_b_proj.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.q_b_proj.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.unembed_out.biases": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.unembed_out.scales": "model-00006-of-00007.safetensors",
|
|
"model.layers.46.self_attn.unembed_out.weight": "model-00006-of-00007.safetensors",
|
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.5.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.6.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.gate.e_score_correction_bias": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.gate.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.7.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.8.self_attn.embed_q.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.embed_q.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.embed_q.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.o_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_a_layernorm.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_a_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_a_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_a_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_b_proj.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_b_proj.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.q_b_proj.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.unembed_out.biases": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.unembed_out.scales": "model-00001-of-00007.safetensors",
|
|
"model.layers.8.self_attn.unembed_out.weight": "model-00001-of-00007.safetensors",
|
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.gate.e_score_correction_bias": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.gate.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.embed_q.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.embed_q.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.embed_q.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.o_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.o_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_a_layernorm.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_a_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_a_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_a_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_b_proj.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_b_proj.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.q_b_proj.weight": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.unembed_out.biases": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.unembed_out.scales": "model-00002-of-00007.safetensors",
|
|
"model.layers.9.self_attn.unembed_out.weight": "model-00002-of-00007.safetensors",
|
|
"model.norm.weight": "model-00007-of-00007.safetensors"
|
|
}
|
|
} |