Qwen-72B-Chat-2bit / config.json
keyfan's picture
Update config.json
a08d63a
{
"_name_or_path": "qwen/Qwen-72B-Chat/",
"architectures": [
"QWenLMHeadModel"
],
"attn_dropout_prob": 0.0,
"auto_map": {
"AutoConfig": "configuration_qwen.QWenConfig",
"AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
},
"bf16": false,
"emb_dropout_prob": 0.0,
"fp16": true,
"fp32": false,
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 49152,
"kv_channels": 128,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 32768,
"model_type": "qwen",
"no_bias": true,
"num_attention_heads": 64,
"num_hidden_layers": 80,
"onnx_safe": null,
"padded_vocab_size": 152064,
"quantization_config": {
"codebook": "E8P12",
"codesz": 8,
"idx_dtype": "torch.int16",
"merge_suv": true,
"modules_to_not_convert": null,
"quant_method": "QUiP",
"rescale_WH": false,
"use_rand": true
},
"rope_theta": 1000000,
"rotary_emb_base": 1000000,
"rotary_pct": 1.0,
"scale_attn_weights": true,
"seq_length": 32768,
"softmax_in_fp32": false,
"tie_word_embeddings": false,
"tokenizer_type": "QWenTokenizer",
"torch_dtype": "float16",
"transformers_version": "4.36.1",
"use_cache": true,
"use_cache_kernel": false,
"use_cache_quantization": false,
"use_dynamic_ntk": false,
"use_flash_attn": true,
"use_logn_attn": false,
"vocab_size": 152064
}