|
{ |
|
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelszjftwc1245dh0l__", |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"GPT2LMHeadModel" |
|
], |
|
"attn_pdrop": 0.1, |
|
"bos_token_id": 50256, |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 50256, |
|
"initializer_range": 0.01, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "gpt2", |
|
"n_embd": 4096, |
|
"n_head": 32, |
|
"n_inner": 16384, |
|
"n_layer": 24, |
|
"n_positions": 2048, |
|
"quantization_config": { |
|
"_load_in_4bit": false, |
|
"_load_in_8bit": true, |
|
"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": false, |
|
"load_in_8bit": true, |
|
"quant_method": "bitsandbytes" |
|
}, |
|
"reorder_and_upcast_attn": false, |
|
"resid_pdrop": 0.1, |
|
"scale_attn_by_inverse_layer_idx": false, |
|
"scale_attn_weights": true, |
|
"summary_activation": null, |
|
"summary_first_dropout": 0.1, |
|
"summary_proj_to_labels": true, |
|
"summary_type": "cls_index", |
|
"summary_use_proj": true, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.42.4", |
|
"use_cache": true, |
|
"vocab_size": 50257 |
|
} |
|
|