aodhan/homeai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
6a0bae2a0be025c484ad60395c8994e3dad2c873
homeai/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/model.safetensors.index.json
Aodhan Collins 6a0bae2a0b feat(phase-04): Wyoming Satellite integration + OpenClaw HA components 
## Voice Pipeline (P3)
- Replace openWakeWord daemon with Wyoming Satellite approach
- Add Wyoming Satellite service on port 10700 for HA voice pipeline
- Update setup.sh with cross-platform sed compatibility (macOS/Linux)
- Add version field to Kokoro TTS voice info
- Update launchd service loader to use Wyoming Satellite

## Home Assistant Integration (P4)
- Add custom conversation agent component (openclaw_conversation)
  - Fix: Use IntentResponse instead of plain strings (HA API requirement)
  - Support both HTTP API and CLI fallback modes
  - Config flow for easy HA UI setup
- Add OpenClaw bridge scripts (Python + Bash)
- Add ha-ctl utility for HA entity control
  - Fix: Use context manager for token file reading
- Add HA configuration examples and documentation

## Infrastructure
- Add mem0 backup automation (launchd + script)
- Add n8n workflow templates (morning briefing, notification router)
- Add VS Code workspace configuration
- Reorganize model files into categorized folders:
  - lmstudio-community/
  - mlx-community/
  - bartowski/
  - mradermacher/

## Documentation
- Update PROJECT_PLAN.md with Wyoming Satellite architecture
- Update TODO.md with completed Wyoming integration tasks
- Add OPENCLAW_INTEGRATION.md for HA setup guide

## Testing
- Verified Wyoming services running (STT:10300, TTS:10301, Satellite:10700)
- Verified OpenClaw CLI accessibility
- Confirmed cross-platform compatibility fixes
2026-03-08 02:06:37 +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