sharpenb's picture
Upload folder using huggingface_hub (#1)
c541d1c verified
raw
history blame
1.32 kB
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsl07ahlnoi8xqlpdb",
"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": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": [
"lm_head"
],
"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": "float16",
"transformers_version": "4.40.0",
"use_cache": false,
"vocab_size": 51200
}