Qwen-7B-4bit / config.json
reyvan's picture
AutoGPTQ model for Qwen/Qwen-7B: 4bits, gr128, desc_act=False
a4ce543 verified
raw
history blame
1.44 kB
{
"_name_or_path": "Qwen/Qwen-7B",
"architectures": [
"QWenLMHeadModel"
],
"attn_dropout_prob": 0.0,
"auto_map": {
"AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
"AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
},
"bf16": true,
"emb_dropout_prob": 0.0,
"fp16": false,
"fp32": false,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 22016,
"kv_channels": 128,
"layer_norm_epsilon": 1e-06,
"max_position_embeddings": 32768,
"model_type": "qwen",
"no_bias": true,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"onnx_safe": null,
"quantization_config": {
"bits": 4,
"damp_percent": 0.01,
"desc_act": false,
"group_size": 128,
"is_marlin_format": false,
"model_file_base_name": "gptq_model-4bit-128g",
"model_name_or_path": "Qwen-7B-4bit",
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"scale_attn_weights": true,
"seq_length": 8192,
"softmax_in_fp32": false,
"tie_word_embeddings": false,
"tokenizer_class": "QWenTokenizer",
"torch_dtype": "float16",
"transformers_version": "4.37.2",
"use_cache": true,
"use_cache_kernel": false,
"use_cache_quantization": false,
"use_dynamic_ntk": true,
"use_flash_attn": true,
"use_logn_attn": true,
"vocab_size": 151936
}