|
{ |
|
"_name_or_path": "skt/kogpt2-base-v2", |
|
"_num_labels": 1, |
|
"activation_function": "gelu_new", |
|
"architectures": [ |
|
"GPT2LMHeadModel" |
|
], |
|
"attn_pdrop": 0.1, |
|
"author": "Heewon Jeon(madjakarta@gmail.com)", |
|
"bos_token_id": 0, |
|
"created_date": "2021-04-28", |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 1, |
|
"gradient_checkpointing": false, |
|
"id2label": { |
|
"0": "LABEL_0" |
|
}, |
|
"initializer_range": 0.02, |
|
"label2id": { |
|
"LABEL_0": 0 |
|
}, |
|
"layer_norm_epsilon": 1e-05, |
|
"license": "CC-BY-NC-SA 4.0", |
|
"model_type": "gpt2", |
|
"n_ctx": 1024, |
|
"n_embd": 768, |
|
"n_head": 12, |
|
"n_inner": null, |
|
"n_layer": 12, |
|
"n_positions": 1024, |
|
"pad_token_id": 3, |
|
"pretraining_tp": 1, |
|
"quantization_config": { |
|
"_load_in_4bit": true, |
|
"_load_in_8bit": false, |
|
"bnb_4bit_compute_dtype": "bfloat16", |
|
"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" |
|
}, |
|
"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, |
|
"task_specific_params": { |
|
"text-generation": { |
|
"do_sample": true, |
|
"max_length": 50 |
|
} |
|
}, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.40.1", |
|
"use_cache": false, |
|
"vocab_size": 51200 |
|
} |
|
|