|
{
|
|
"_name_or_path": "microsoft/phi-2",
|
|
"activation_function": "gelu_new",
|
|
"architectures": [
|
|
"PhiForCausalLM"
|
|
],
|
|
"attn_pdrop": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
|
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
|
},
|
|
"embd_pdrop": 0.0,
|
|
"flash_attn": true,
|
|
"flash_rotary": true,
|
|
"fused_dense": true,
|
|
"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,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"_load_in_4bit": true,
|
|
"_load_in_8bit": false,
|
|
"bnb_4bit_compute_dtype": "float16",
|
|
"bnb_4bit_quant_storage": "uint8",
|
|
"bnb_4bit_quant_type": "nf4",
|
|
"bnb_4bit_use_double_quant": false,
|
|
"llm_int8_enable_fp32_cpu_offload": false,
|
|
"llm_int8_has_fp16_weight": false,
|
|
"llm_int8_skip_modules": null,
|
|
"llm_int8_threshold": 6.0,
|
|
"load_in_4bit": true,
|
|
"load_in_8bit": false,
|
|
"quant_method": "bitsandbytes"
|
|
},
|
|
"resid_pdrop": 0.1,
|
|
"rotary_dim": 32,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.44.0",
|
|
"use_cache": false,
|
|
"vocab_size": 51200
|
|
}
|
|
|