{ | |
"_name_or_path": "/mnt/kaiwu-group-pp-sh/edge_llm/distill_hf/1118-phi2-tie-emb-unfreeze-decoder-use-qwen-vocab-1.5e-4-2k-seq-tp1/anchor/", | |
"architectures": [ | |
"PhiForCausalLM" | |
], | |
"attention_dropout": 0.0, | |
"auto_map": { | |
"AutoConfig": "configuration_phi.PhiConfig", | |
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM" | |
}, | |
"bos_token_id": 151643, | |
"embd_pdrop": 0.0, | |
"eos_token_id": 151645, | |
"hidden_act": "gelu", | |
"hidden_size": 2560, | |
"initializer_range": 0.02, | |
"intermediate_size": 10240, | |
"layer_norm_eps": 1e-05, | |
"max_position_embeddings": 2048, | |
"model_type": "phi", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 32, | |
"num_key_value_heads": 32, | |
"partial_rotary_factor": 0.4, | |
"qk_layernorm": false, | |
"resid_pdrop": 0.1, | |
"rope_scaling": null, | |
"rope_theta": 10000.0, | |
"tie_word_embeddings": true, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.43.3", | |
"use_cache": true, | |
"vocab_size": 152064 | |
} | |