quantized_gpt2 / config.json
appy1234's picture
Upload model
296579c verified
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"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": {
"include_input_output_embeddings": false,
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"group_size": 128,
"layout": {
"_data": {
"inner_k_tiles": 8
},
"_type": "TensorCoreTiledLayout",
"_version": 1
},
"packing_format": {
"_data": "PLAIN",
"_type": "PackingFormat"
},
"preserve_zero": null,
"set_inductor_config": true,
"use_hqq": false,
"zero_point_domain": {
"_data": "NONE",
"_type": "ZeroPointDomain"
}
},
"_type": "Int4WeightOnlyConfig",
"_version": 1
}
},
"quant_type_kwargs": {},
"untie_embedding_weights": false
},
"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
}
},
"transformers_version": "4.56.1",
"use_cache": true,
"vocab_size": 50257
}