Qwen-14B-Chat-GPTQ / config.json
TheBloke's picture
GPTQ model commit
04fe772
raw
history blame
1.87 kB
{
"_name_or_path": "/workspace/process/qwen_qwen-14b-chat/source",
"architectures": [
"QWenLMHeadModel"
],
"attn_dropout_prob": 0.0,
"auto_map": {
"AutoConfig": "configuration_qwen.QWenConfig",
"AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
},
"bf16": true,
"emb_dropout_prob": 0.0,
"fp16": false,
"fp32": false,
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27392,
"kv_channels": 128,
"layer_norm_epsilon": 1e-06,
"max_position_embeddings": 8192,
"model_type": "qwen",
"no_bias": true,
"num_attention_heads": 40,
"num_hidden_layers": 40,
"onnx_safe": null,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": "transformer.h",
"damp_percent": 0.1,
"desc_act": true,
"disable_exllama": false,
"group_size": 32,
"max_input_length": null,
"model_seqlen": 8192,
"module_name_preceding_first_block": [
"transformer.wte",
"transformer.drop",
"transformer.rotary_emb"
],
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": false
},
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"scale_attn_weights": true,
"seq_length": 2048,
"softmax_in_fp32": false,
"tie_word_embeddings": false,
"tokenizer_class": "QWenTokenizer",
"torch_dtype": "bfloat16",
"transformers_version": "4.34.1",
"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": 152064
}