|
{
|
|
"_name_or_path": "C:\\Users\\ov-user\\Documents\\python_projects\\awq_quantized_models\\awq_calibset_by_authors/opt-6.7b-AWQ-4bits-128g-wikitext2",
|
|
"_remove_final_layer_norm": false,
|
|
"activation_dropout": 0.0,
|
|
"activation_function": "relu",
|
|
"architectures": [
|
|
"OPTForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 2,
|
|
"do_layer_norm_before": true,
|
|
"dropout": 0.1,
|
|
"enable_bias": true,
|
|
"eos_token_id": 2,
|
|
"ffn_dim": 16384,
|
|
"hidden_size": 4096,
|
|
"init_std": 0.02,
|
|
"layer_norm_elementwise_affine": true,
|
|
"layerdrop": 0.0,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "opt",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"pad_token_id": 1,
|
|
"prefix": "</s>",
|
|
"quantization_config": {
|
|
"backend": "autoawq",
|
|
"bits": 4,
|
|
"do_fuse": false,
|
|
"exllama_config": null,
|
|
"fuse_max_seq_len": null,
|
|
"group_size": 128,
|
|
"modules_to_fuse": null,
|
|
"modules_to_not_convert": null,
|
|
"quant_method": "awq",
|
|
"version": "gemm",
|
|
"zero_point": true
|
|
},
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.41.0.dev0",
|
|
"use_cache": false,
|
|
"vocab_size": 50272,
|
|
"word_embed_proj_dim": 4096
|
|
}
|
|
|