phi-2-bnb-4bit / config.json
evaldas-leliuga's picture
Added model
e308a25 verified
raw
history blame
1.28 kB
{
"_name_or_path": "microsoft/phi-2",
"architectures": [
"PhiForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
},
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"hidden_act": "gelu_new",
"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,
"quantization_config": {
"bnb_4bit_compute_dtype": "float16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"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,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 51200
}