60 lines
1.4 KiB
JSON
60 lines
1.4 KiB
JSON
|
{
|
||
|
|
"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": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 22016,
|
||
|
|
"kv_channels": 128,
|
||
|
|
"layer_norm_epsilon": 1e-06,
|
||
|
|
"max_position_embeddings": 8192,
|
||
|
|
"model_type": "qwen",
|
||
|
|
"no_bias": true,
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"onnx_safe": null,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 4,
|
||
|
|
"group_size": 128,
|
||
|
|
"damp_percent": 0.01,
|
||
|
|
"desc_act": false,
|
||
|
|
"static_groups": false,
|
||
|
|
"sym": true,
|
||
|
|
"true_sequential": true,
|
||
|
|
"model_name_or_path": null,
|
||
|
|
"model_file_base_name": "model",
|
||
|
|
"quant_method": "gptq"
|
||
|
|
},
|
||
|
|
"rotary_emb_base": 10000,
|
||
|
|
"rotary_pct": 1.0,
|
||
|
|
"scale_attn_weights": true,
|
||
|
|
"seq_length": 2048,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"tokenizer_type": "QWenTokenizer",
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.32.0",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_dynamic_ntk": true,
|
||
|
|
"use_flash_attn": "auto",
|
||
|
|
"use_logn_attn": true,
|
||
|
|
"visual": {
|
||
|
|
"heads": 16,
|
||
|
|
"image_size": 448,
|
||
|
|
"image_start_id": 151857,
|
||
|
|
"layers": 48,
|
||
|
|
"mlp_ratio": 4.9231,
|
||
|
|
"output_dim": 4096,
|
||
|
|
"patch_size": 14,
|
||
|
|
"width": 1664
|
||
|
|
},
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|