gpt2-safety-GPTQ-8bit / config.json
Luca-Engel's picture
AutoGPTQ model for gpt2-dpo: 8bits, gr128, desc_act=False
65933e0 verified
raw
history blame
1.27 kB
{
"_name_or_path": "mNLP-project/gpt2-finetuned-mcqa-sciq2-safety",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"quantization_config": {
"bits": 8,
"damp_percent": 0.01,
"desc_act": false,
"group_size": 128,
"is_marlin_format": false,
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"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": "4.41.2",
"use_cache": true,
"vocab_size": 50257
}