croissant_small_models
/
DSAutotuneConfig.false+DataMix.frplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false
/hf_model
/pytorch_model.bin.index.json
{ | |
"weight_map": { | |
"model.embed_tokens.weight": "pytorch_model.bin", | |
"model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin", | |
"model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin", | |
"model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin", | |
"model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin", | |
"model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin", | |
"model.layers.0.mlp.up_proj.weight": "pytorch_model.bin", | |
"model.layers.0.mlp.down_proj.weight": "pytorch_model.bin", | |
"model.layers.0.input_layernorm.weight": "pytorch_model.bin", | |
"model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin", | |
"model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin", | |
"model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin", | |
"model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin", | |
"model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin", | |
"model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin", | |
"model.layers.1.mlp.up_proj.weight": "pytorch_model.bin", | |
"model.layers.1.mlp.down_proj.weight": "pytorch_model.bin", | |
"model.layers.1.input_layernorm.weight": "pytorch_model.bin", | |
"model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin", | |
"model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin", | |
"model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin", | |
"model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin", | |
"model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin", | |
"model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin", | |
"model.layers.2.mlp.up_proj.weight": "pytorch_model.bin", | |
"model.layers.2.mlp.down_proj.weight": "pytorch_model.bin", | |
"model.layers.2.input_layernorm.weight": "pytorch_model.bin", | |
"model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin", | |
"model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin", | |
"model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin", | |
"model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin", | |
"model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin", | |
"model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin", | |
"model.layers.3.mlp.up_proj.weight": "pytorch_model.bin", | |
"model.layers.3.mlp.down_proj.weight": "pytorch_model.bin", | |
"model.layers.3.input_layernorm.weight": "pytorch_model.bin", | |
"model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin", | |
"model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin", | |
"model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin", | |
"model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin", | |
"model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin", | |
"model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin", | |
"model.layers.4.mlp.up_proj.weight": "pytorch_model.bin", | |
"model.layers.4.mlp.down_proj.weight": "pytorch_model.bin", | |
"model.layers.4.input_layernorm.weight": "pytorch_model.bin", | |
"model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin", | |
"model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin", | |
"model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin", | |
"model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin", | |
"model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin", | |
"model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin", | |
"model.layers.5.mlp.up_proj.weight": "pytorch_model.bin", | |
"model.layers.5.mlp.down_proj.weight": "pytorch_model.bin", | |
"model.layers.5.input_layernorm.weight": "pytorch_model.bin", | |
"model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin", | |
"model.norm.weight": "pytorch_model.bin", | |
"lm_head.weight": "pytorch_model.bin" | |
}, | |
"metadata": { | |
"total_size": 664850432 | |
} | |
} |