| {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 3531735040}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "transformer.h.0.input_layernorm.bias": "model-00001-of-00004.safetensors", "transformer.h.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors", "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors", "transformer.h.0.self_attention.dense.weight": "model-00001-of-00004.safetensors", "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00004.safetensors", "transformer.h.1.input_layernorm.bias": "model-00001-of-00004.safetensors", "transformer.h.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors", "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors", "transformer.h.1.self_attention.dense.weight": "model-00002-of-00004.safetensors", "transformer.h.1.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors", "transformer.h.2.input_layernorm.bias": "model-00002-of-00004.safetensors", "transformer.h.2.input_layernorm.weight": "model-00002-of-00004.safetensors", "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors", "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors", "transformer.h.2.self_attention.dense.weight": "model-00002-of-00004.safetensors", "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00004.safetensors", "transformer.h.3.input_layernorm.bias": "model-00002-of-00004.safetensors", "transformer.h.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors", "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors", "transformer.h.3.self_attention.dense.weight": "model-00003-of-00004.safetensors", "transformer.h.3.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors", "transformer.h.4.input_layernorm.bias": "model-00003-of-00004.safetensors", "transformer.h.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors", "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors", "transformer.h.4.self_attention.dense.weight": "model-00003-of-00004.safetensors", "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors", "transformer.h.5.input_layernorm.bias": "model-00003-of-00004.safetensors", "transformer.h.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors", "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors", "transformer.h.5.self_attention.dense.weight": "model-00003-of-00004.safetensors", "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00004.safetensors", "transformer.h.6.input_layernorm.bias": "model-00003-of-00004.safetensors", "transformer.h.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors", "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors", "transformer.h.6.self_attention.dense.weight": "model-00004-of-00004.safetensors", "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00004.safetensors", "transformer.ln_f.bias": "model-00004-of-00004.safetensors", "transformer.ln_f.weight": "model-00004-of-00004.safetensors", "transformer.word_embeddings.weight": "model-00004-of-00004.safetensors"}} |