|
{ |
|
"_name_or_path": "/models/phi-2", |
|
"activation_function": "gelu_new", |
|
"architectures": [ |
|
"PhiForCausalLM" |
|
], |
|
"attn_pdrop": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "configuration_phi.PhiConfig", |
|
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM" |
|
}, |
|
"embd_pdrop": 0.0, |
|
"flash_attn": false, |
|
"flash_rotary": false, |
|
"fused_dense": false, |
|
"img_processor": null, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "phi-msft", |
|
"n_embd": 2560, |
|
"n_head": 32, |
|
"n_head_kv": null, |
|
"n_inner": null, |
|
"n_layer": 32, |
|
"n_positions": 2048, |
|
"quantization_config": { |
|
"autoround_version": "0.1", |
|
"bits": 4, |
|
"damp_percent": 0.01, |
|
"desc_act": false, |
|
"enable_minmax_tuning": true, |
|
"group_size": 128, |
|
"is_marlin_format": false, |
|
"iters": 1000, |
|
"lr": 0.001, |
|
"minmax_lr": 0.001, |
|
"model_file_base_name": "model", |
|
"model_name_or_path": null, |
|
"quant_method": "gptq", |
|
"static_groups": false, |
|
"sym": false, |
|
"true_sequential": false, |
|
"use_quant_input": false |
|
}, |
|
"resid_pdrop": 0.1, |
|
"rotary_dim": 32, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.37.2", |
|
"vocab_size": 51200 |
|
} |
|
|