| { | |
| "model_type": "starcoder2", | |
| "architectures": [ | |
| "Starcoder2ForCausalLM" | |
| ], | |
| "pre_weights": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "is_embed": true | |
| } | |
| ], | |
| "post_weights": [ | |
| { | |
| "name": "lm_head.weight", | |
| "is_embed": true, | |
| "aliases": ["model.embed_tokens.weight"] | |
| }, | |
| { | |
| "name": "model.norm.bias" | |
| }, | |
| { | |
| "name": "model.norm.weight" | |
| } | |
| ], | |
| "num_layers_config_key": "num_hidden_layers", | |
| "layer_templates": { | |
| "weights": [ | |
| { | |
| "name": "model.layers.${layer_index}.input_layernorm.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.input_layernorm.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.q_proj.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.q_proj.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.k_proj.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.k_proj.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.v_proj.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.v_proj.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.o_proj.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.self_attn.o_proj.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.post_attention_layernorm.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.post_attention_layernorm.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.mlp.c_fc.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.mlp.c_fc.weight" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.mlp.c_proj.bias" | |
| }, | |
| { | |
| "name": "model.layers.${layer_index}.mlp.c_proj.weight" | |
| } | |
| ] | |
| } | |
| } | |