{ "metadata": { "total_size": 5569925178 }, "weight_map": { "dense_bs.0": "model-00002-of-00002.safetensors", "dense_bs.1": "model-00002-of-00002.safetensors", "dense_bs.10": "model-00002-of-00002.safetensors", "dense_bs.11": "model-00002-of-00002.safetensors", "dense_bs.12": "model-00002-of-00002.safetensors", "dense_bs.13": "model-00002-of-00002.safetensors", "dense_bs.14": "model-00002-of-00002.safetensors", "dense_bs.15": "model-00002-of-00002.safetensors", "dense_bs.16": "model-00002-of-00002.safetensors", "dense_bs.17": "model-00002-of-00002.safetensors", "dense_bs.18": "model-00002-of-00002.safetensors", "dense_bs.19": "model-00002-of-00002.safetensors", "dense_bs.2": "model-00002-of-00002.safetensors", "dense_bs.20": "model-00002-of-00002.safetensors", "dense_bs.21": "model-00002-of-00002.safetensors", "dense_bs.22": "model-00002-of-00002.safetensors", "dense_bs.23": "model-00002-of-00002.safetensors", "dense_bs.24": "model-00002-of-00002.safetensors", "dense_bs.25": "model-00002-of-00002.safetensors", "dense_bs.26": "model-00002-of-00002.safetensors", "dense_bs.27": "model-00002-of-00002.safetensors", "dense_bs.28": "model-00002-of-00002.safetensors", "dense_bs.29": "model-00002-of-00002.safetensors", "dense_bs.3": "model-00002-of-00002.safetensors", "dense_bs.30": "model-00002-of-00002.safetensors", "dense_bs.31": "model-00002-of-00002.safetensors", "dense_bs.4": "model-00002-of-00002.safetensors", "dense_bs.5": "model-00002-of-00002.safetensors", "dense_bs.6": "model-00002-of-00002.safetensors", "dense_bs.7": "model-00002-of-00002.safetensors", "dense_bs.8": "model-00002-of-00002.safetensors", "dense_bs.9": "model-00002-of-00002.safetensors", "dynamic_dense.0.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.0.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.1.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.1.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.10.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.10.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.11.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.11.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.12.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.12.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.13.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.13.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.14.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.14.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.15.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.15.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.16.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.16.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.17.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.17.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.18.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.18.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.19.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.19.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.2.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.2.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.20.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.20.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.21.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.21.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.22.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.22.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.23.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.23.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.24.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.24.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.25.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.25.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.26.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.26.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.27.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.27.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.28.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.28.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.29.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.29.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.3.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.3.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.30.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.30.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.31.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.31.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.4.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.4.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.5.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.5.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.6.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.6.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.7.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.7.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.8.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.8.w2.weight": "model-00002-of-00002.safetensors", "dynamic_dense.9.w1.weight": "model-00002-of-00002.safetensors", "dynamic_dense.9.w2.weight": "model-00002-of-00002.safetensors", "layers.0.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.0.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.0.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.0.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.0.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.0.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.0.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.0.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.0.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.0.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.0.attention_norm.bias": "model-00001-of-00002.safetensors", "layers.0.attention_norm.weight": "model-00001-of-00002.safetensors", "layers.0.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.0.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.0.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.1.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.1.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.1.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.1.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.1.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.1.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.1.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.1.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.1.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.1.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.1.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.1.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.1.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.1.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.1.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.1.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.1.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.1.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.1.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.10.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.10.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.10.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.10.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.10.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.10.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.10.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.10.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.10.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.10.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.10.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.10.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.10.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.10.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.10.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.10.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.10.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.10.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.10.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.11.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.11.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.11.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.11.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.11.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.11.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.11.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.11.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.11.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.11.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.11.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.11.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.11.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.11.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.11.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.11.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.11.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.11.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.11.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.12.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.12.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.12.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.12.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.12.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.12.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.12.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.12.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.12.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.12.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.12.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.12.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.12.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.12.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.12.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.12.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.12.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.12.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.12.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.13.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.13.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.13.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.13.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.13.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.13.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.13.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.13.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.13.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.13.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.13.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.13.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.13.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.13.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.13.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.13.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.13.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.13.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.13.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.14.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.14.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.14.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.14.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.14.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.14.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.14.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.14.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.14.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.14.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.14.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.14.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.14.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.14.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.14.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.14.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.14.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.14.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.14.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.15.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.15.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.15.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.15.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.15.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.15.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.15.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.15.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.15.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.15.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.15.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.15.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.15.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.15.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.15.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.15.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.15.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.15.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.15.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.16.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.16.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.16.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.16.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.16.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.16.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.16.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.16.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.16.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.16.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.16.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.16.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.16.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.16.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.16.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.16.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.16.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.16.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.16.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.17.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.17.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.17.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.17.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.17.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.17.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.17.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.17.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.17.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.17.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.17.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.17.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.17.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.17.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.17.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.17.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.17.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.17.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.17.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.18.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.18.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.18.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.18.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.18.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.18.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.18.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.18.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.18.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.18.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.18.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.18.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.18.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.18.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.18.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.18.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.18.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.18.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.18.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.19.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.19.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.19.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.19.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.19.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.19.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.19.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.19.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.19.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.19.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.19.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.19.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.19.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.19.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.19.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.19.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.19.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.19.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.19.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.2.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.2.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.2.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.2.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.2.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.2.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.2.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.2.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.2.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.2.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.2.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.2.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.2.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.2.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.2.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.2.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.2.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.2.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.2.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.20.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.20.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.20.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.20.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.20.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.20.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.20.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.20.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.20.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.20.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.20.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.20.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.20.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.20.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.20.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.20.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.20.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.20.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.20.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.20.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.21.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.21.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.21.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.21.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.21.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.21.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.21.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.21.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.21.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.21.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.21.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.21.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.21.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.21.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.21.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.21.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.21.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.21.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.21.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.21.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.21.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.22.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.22.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.22.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.22.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.22.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.22.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.22.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.22.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.22.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.22.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.22.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.22.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.22.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.22.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.22.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.22.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.22.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.22.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.22.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.22.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.22.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.23.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.23.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.23.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.23.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.23.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.23.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.23.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.23.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.23.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.23.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.23.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.23.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.23.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.23.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.23.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.23.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.23.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.23.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.23.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.23.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.23.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.24.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.24.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.24.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.24.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.24.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.24.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.24.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.24.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.24.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.24.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.24.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.24.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.24.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.24.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.24.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.24.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.24.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.24.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.24.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.24.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.24.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.24.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.25.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.25.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.25.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.25.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.25.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.25.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.25.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.25.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.25.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.25.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.25.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.25.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.25.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.25.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.25.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.25.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.25.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.25.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.25.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.25.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.25.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.25.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.26.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.26.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.26.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.26.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.26.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.26.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.26.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.26.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.26.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.26.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.26.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.26.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.26.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.26.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.26.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.26.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.26.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.26.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.26.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.26.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.26.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.26.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.27.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.27.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.27.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.27.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.27.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.27.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.27.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.27.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.27.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.27.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.27.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.27.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.27.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.27.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.27.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.27.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.27.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.27.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.27.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.27.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.27.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.27.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.28.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.28.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.28.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.28.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.28.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.28.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.28.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.28.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.28.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.28.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.28.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.28.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.28.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.28.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.28.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.28.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.28.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.28.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.28.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.28.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.28.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.28.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.29.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.29.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.29.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.29.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.29.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.29.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.29.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.29.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.29.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.29.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.29.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.29.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.29.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.29.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.29.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.29.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.29.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.29.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.29.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.29.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.29.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.29.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.3.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.3.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.3.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.3.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.3.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.3.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.3.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.3.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.3.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.3.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.3.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.3.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.3.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.3.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.3.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.3.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.3.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.3.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.3.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.30.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.30.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.30.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.30.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.30.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.30.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.30.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.30.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.30.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.30.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.30.attention_norms.0.bias": "model-00002-of-00002.safetensors", "layers.30.attention_norms.0.weight": "model-00002-of-00002.safetensors", "layers.30.attention_norms.1.bias": "model-00002-of-00002.safetensors", "layers.30.attention_norms.1.weight": "model-00002-of-00002.safetensors", "layers.30.attention_norms.2.bias": "model-00002-of-00002.safetensors", "layers.30.attention_norms.2.weight": "model-00002-of-00002.safetensors", "layers.30.feed_forward.w1.bias": "model-00002-of-00002.safetensors", "layers.30.feed_forward.w1.weight": "model-00002-of-00002.safetensors", "layers.30.feed_forward.w2.bias": "model-00002-of-00002.safetensors", "layers.30.feed_forward.w2.weight": "model-00002-of-00002.safetensors", "layers.30.ffn_norm.bias": "model-00002-of-00002.safetensors", "layers.30.ffn_norm.weight": "model-00002-of-00002.safetensors", "layers.31.attention.k_norm.weight": "model-00002-of-00002.safetensors", "layers.31.attention.q_norm.weight": "model-00002-of-00002.safetensors", "layers.31.attention.wk.bias": "model-00002-of-00002.safetensors", "layers.31.attention.wk.weight": "model-00002-of-00002.safetensors", "layers.31.attention.wo.bias": "model-00002-of-00002.safetensors", "layers.31.attention.wo.weight": "model-00002-of-00002.safetensors", "layers.31.attention.wq.bias": "model-00002-of-00002.safetensors", "layers.31.attention.wq.weight": "model-00002-of-00002.safetensors", "layers.31.attention.wv.bias": "model-00002-of-00002.safetensors", "layers.31.attention.wv.weight": "model-00002-of-00002.safetensors", "layers.31.attention_norms.0.bias": "model-00002-of-00002.safetensors", "layers.31.attention_norms.0.weight": "model-00002-of-00002.safetensors", "layers.31.attention_norms.1.bias": "model-00002-of-00002.safetensors", "layers.31.attention_norms.1.weight": "model-00002-of-00002.safetensors", "layers.31.attention_norms.2.bias": "model-00002-of-00002.safetensors", "layers.31.attention_norms.2.weight": "model-00002-of-00002.safetensors", "layers.31.feed_forward.w1.bias": "model-00002-of-00002.safetensors", "layers.31.feed_forward.w1.weight": "model-00002-of-00002.safetensors", "layers.31.feed_forward.w2.bias": "model-00002-of-00002.safetensors", "layers.31.feed_forward.w2.weight": "model-00002-of-00002.safetensors", "layers.31.ffn_norm.bias": "model-00002-of-00002.safetensors", "layers.31.ffn_norm.weight": "model-00002-of-00002.safetensors", "layers.4.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.4.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.4.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.4.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.4.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.4.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.4.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.4.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.4.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.4.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.4.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.4.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.4.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.4.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.4.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.4.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.4.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.4.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.4.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.5.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.5.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.5.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.5.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.5.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.5.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.5.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.5.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.5.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.5.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.5.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.5.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.5.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.5.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.5.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.5.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.5.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.5.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.5.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.6.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.6.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.6.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.6.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.6.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.6.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.6.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.6.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.6.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.6.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.6.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.6.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.6.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.6.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.6.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.6.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.6.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.6.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.6.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.7.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.7.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.7.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.7.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.7.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.7.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.7.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.7.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.7.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.7.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.7.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.7.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.7.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.7.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.7.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.7.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.7.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.7.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.7.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.8.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.8.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.8.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.8.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.8.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.8.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.8.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.8.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.8.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.8.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.8.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.8.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.8.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.8.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.8.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.8.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.8.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.8.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.8.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors", "layers.9.attention.k_norm.weight": "model-00001-of-00002.safetensors", "layers.9.attention.q_norm.weight": "model-00001-of-00002.safetensors", "layers.9.attention.wk.bias": "model-00001-of-00002.safetensors", "layers.9.attention.wk.weight": "model-00001-of-00002.safetensors", "layers.9.attention.wo.bias": "model-00001-of-00002.safetensors", "layers.9.attention.wo.weight": "model-00001-of-00002.safetensors", "layers.9.attention.wq.bias": "model-00001-of-00002.safetensors", "layers.9.attention.wq.weight": "model-00001-of-00002.safetensors", "layers.9.attention.wv.bias": "model-00001-of-00002.safetensors", "layers.9.attention.wv.weight": "model-00001-of-00002.safetensors", "layers.9.attention_norms.0.bias": "model-00001-of-00002.safetensors", "layers.9.attention_norms.0.weight": "model-00001-of-00002.safetensors", "layers.9.attention_norms.1.bias": "model-00001-of-00002.safetensors", "layers.9.attention_norms.1.weight": "model-00001-of-00002.safetensors", "layers.9.attention_norms.2.bias": "model-00001-of-00002.safetensors", "layers.9.attention_norms.2.weight": "model-00001-of-00002.safetensors", "layers.9.feed_forward.w1.bias": "model-00001-of-00002.safetensors", "layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors", "layers.9.feed_forward.w2.bias": "model-00001-of-00002.safetensors", "layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors", "layers.9.ffn_norm.bias": "model-00001-of-00002.safetensors", "layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors", "norm.bias": "model-00002-of-00002.safetensors", "norm.weight": "model-00002-of-00002.safetensors", "output.weight": "model-00002-of-00002.safetensors", "tok_embeddings.weight": "model-00001-of-00002.safetensors" } }