model.safetensors.index.json

{
  "metadata": {
    "total_size": 50294252544
  },
  "weight_map": {
    "transformer.embedding.word_embeddings.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.final_layernorm.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.final_layernorm.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.0.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.0.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.1.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.10.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.10.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.11.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.12.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.13.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.14.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.14.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.14.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.15.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.16.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.17.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.18.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.19.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.2.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.2.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.20.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.dense.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.dense.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.query_key_value.weight_scale": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.20.self_attention.rotary_emb.inv_freq": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.21.input_layernorm.bias": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.21.input_layernorm.weight": "model-00003-of-00011.safetensors",
    "transformer.encoder.layers.21.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.21.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.22.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.23.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.24.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.25.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.26.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.dense.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.dense.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.query_key_value.weight_scale": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.27.self_attention.rotary_emb.inv_freq": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.28.input_layernorm.bias": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.28.input_layernorm.weight": "model-00004-of-00011.safetensors",
    "transformer.encoder.layers.28.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.28.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.29.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.3.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.3.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.30.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.30.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.31.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.32.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.33.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.dense.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.dense.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.query_key_value.weight_scale": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.34.self_attention.rotary_emb.inv_freq": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.35.input_layernorm.bias": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.35.input_layernorm.weight": "model-00005-of-00011.safetensors",
    "transformer.encoder.layers.35.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.35.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.36.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.37.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.38.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.39.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.4.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.4.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.40.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.40.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.mlp.dense_4h_to_h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.mlp.dense_h_to_4h.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.dense.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.dense.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.dense.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.query_key_value.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.query_key_value.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.query_key_value.weight_scale": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.41.self_attention.rotary_emb.inv_freq": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.42.input_layernorm.bias": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.42.input_layernorm.weight": "model-00006-of-00011.safetensors",
    "transformer.encoder.layers.42.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.42.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.43.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.44.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.45.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.46.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.47.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.mlp.dense_4h_to_h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.mlp.dense_h_to_4h.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.dense.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.dense.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.dense.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.query_key_value.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.query_key_value.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.query_key_value.weight_scale": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.48.self_attention.rotary_emb.inv_freq": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.49.input_layernorm.bias": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.49.input_layernorm.weight": "model-00007-of-00011.safetensors",
    "transformer.encoder.layers.49.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.49.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.5.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.5.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.50.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.50.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.51.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.52.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.53.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.54.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.mlp.dense_4h_to_h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.mlp.dense_h_to_4h.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.dense.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.dense.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.dense.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.query_key_value.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.query_key_value.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.query_key_value.weight_scale": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.55.self_attention.rotary_emb.inv_freq": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.56.input_layernorm.bias": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.56.input_layernorm.weight": "model-00008-of-00011.safetensors",
    "transformer.encoder.layers.56.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.56.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.57.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.58.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.59.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.6.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.post_attention_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.dense.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.dense.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.query_key_value.weight_scale": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.6.self_attention.rotary_emb.inv_freq": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.60.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.60.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.61.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.mlp.dense_4h_to_h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.mlp.dense_h_to_4h.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.dense.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.dense.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.dense.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.query_key_value.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.query_key_value.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.query_key_value.weight_scale": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.62.self_attention.rotary_emb.inv_freq": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.63.input_layernorm.bias": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.63.input_layernorm.weight": "model-00009-of-00011.safetensors",
    "transformer.encoder.layers.63.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.63.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.64.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.65.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.66.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.67.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.68.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.mlp.dense_4h_to_h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.mlp.dense_4h_to_h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.mlp.dense_4h_to_h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.mlp.dense_h_to_4h.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.mlp.dense_h_to_4h.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.mlp.dense_h_to_4h.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.post_attention_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.dense.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.dense.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.dense.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.query_key_value.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.query_key_value.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.query_key_value.weight_scale": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.69.self_attention.rotary_emb.inv_freq": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.7.input_layernorm.bias": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.7.input_layernorm.weight": "model-00001-of-00011.safetensors",
    "transformer.encoder.layers.7.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.7.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.70.input_layernorm.bias": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.70.input_layernorm.weight": "model-00010-of-00011.safetensors",
    "transformer.encoder.layers.70.mlp.dense_4h_to_h.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.mlp.dense_4h_to_h.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.mlp.dense_4h_to_h.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.mlp.dense_h_to_4h.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.mlp.dense_h_to_4h.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.mlp.dense_h_to_4h.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.post_attention_layernorm.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.dense.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.dense.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.dense.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.query_key_value.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.query_key_value.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.query_key_value.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.70.self_attention.rotary_emb.inv_freq": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.input_layernorm.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.input_layernorm.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.mlp.dense_4h_to_h.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.mlp.dense_4h_to_h.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.mlp.dense_4h_to_h.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.mlp.dense_h_to_4h.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.mlp.dense_h_to_4h.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.mlp.dense_h_to_4h.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.post_attention_layernorm.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.dense.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.dense.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.dense.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.query_key_value.bias": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.query_key_value.weight": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.query_key_value.weight_scale": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.71.self_attention.rotary_emb.inv_freq": "model-00011-of-00011.safetensors",
    "transformer.encoder.layers.8.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.8.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.input_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.input_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.dense.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.dense.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.query_key_value.weight_scale": "model-00002-of-00011.safetensors",
    "transformer.encoder.layers.9.self_attention.rotary_emb.inv_freq": "model-00002-of-00011.safetensors",
    "transformer.output_layer.weight": "model-00011-of-00011.safetensors"
  }
}