| { |
| "metadata": { |
| "total_size": 6143247366 |
| }, |
| "weight_map": { |
| "lm_head.bias": "model-00002-of-00002.safetensors", |
| "lm_head.weight": "model-00002-of-00002.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", |
| "model.final_layernorm.bias": "model-00002-of-00002.safetensors", |
| "model.final_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.halting.halt_predictor.0.bias": "model-00002-of-00002.safetensors", |
| "model.halting.halt_predictor.0.weight": "model-00002-of-00002.safetensors", |
| "model.halting.halt_predictor.2.bias": "model-00002-of-00002.safetensors", |
| "model.halting.halt_predictor.2.weight": "model-00002-of-00002.safetensors", |
| "model.input_gate.gate.0.bias": "model-00002-of-00002.safetensors", |
| "model.input_gate.gate.0.weight": "model-00002-of-00002.safetensors", |
| "model.input_gate.gate.3.bias": "model-00002-of-00002.safetensors", |
| "model.input_gate.gate.3.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.14.input_layernorm.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.dense.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.dense.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.input_layernorm.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.dense.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.dense.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.post_reasoning_layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.post_reasoning_layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.pre_reasoning_layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.cross_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.mlp.0.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.mlp.0.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.mlp.3.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.mlp.3.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.mlp_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.mlp_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.0.self_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.cross_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.mlp.0.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.mlp.0.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.mlp.3.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.mlp.3.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.mlp_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.mlp_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.1.self_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.cross_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.mlp.0.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.mlp.0.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.mlp.3.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.mlp.3.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.mlp_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.mlp_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.2.self_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.cross_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.mlp.0.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.mlp.0.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.mlp.3.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.mlp.3.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.mlp_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.mlp_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn_norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_blocks.3.self_attn_norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.cross_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.gate_scale": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.norm.bias": "model-00002-of-00002.safetensors", |
| "model.reasoning_injector.norm.weight": "model-00002-of-00002.safetensors", |
| "model.reasoning_tokens.embeddings": "model-00002-of-00002.safetensors", |
| "model.reasoning_tokens.step_embeddings.weight": "model-00002-of-00002.safetensors" |
| } |
| } |
|
|
