vicuna-33B-GPTQ / config.json
TheBloke's picture
Update for Transformers GPTQ support
4b357f8
raw
history blame
837 Bytes
{
"_name_or_path": "/home/ubuntu/model_weights/vicuna-33b-gpt4-20230521/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 6656,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 52,
"num_hidden_layers": 60,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 32000,
"quantization_config": {
"bits": 3,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model",
"quant_method": "gptq"
}
}