aodhan/homeai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
9eb563311533b577febfc50ffb227612a0dcf1c9
homeai/homeai-llm/modelfiles/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/model.safetensors.index.json
Aodhan Collins c4f3dbed77 Phase 4: OpenClaw agent setup + expanded model catalog 
- 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>
2026-03-06 00:03:06 +00:00

922 lines
83 KiB
JSON
Raw Blame History

{
"metadata": {
"total_size": 8839977984
},
"weight_map": {
"lm_head.biases": "model-00002-of-00002.safetensors",
"lm_head.scales": "model-00002-of-00002.safetensors",
"lm_head.weight": "model-00002-of-00002.safetensors",
"model.embed_tokens.biases": "model-00001-of-00002.safetensors",
"model.embed_tokens.scales": "model-00001-of-00002.safetensors",
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.16.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.gate.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors"
}
}
Reference in New Issue View Git Blame Copy Permalink