37 lines
910 B
JSON
37 lines
910 B
JSON
{
|
|
"architectures": [
|
|
"QWenLMHeadModel"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_qwen.QWenConfig",
|
|
"AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
|
|
},
|
|
"attn_dropout_prob": 0.0,
|
|
"bf16": false,
|
|
"emb_dropout_prob": 0.0,
|
|
"fp16": false,
|
|
"fp32": false,
|
|
"hidden_size": 2048,
|
|
"intermediate_size": 11008,
|
|
"initializer_range": 0.02,
|
|
"kv_channels": 128,
|
|
"layer_norm_epsilon": 1e-06,
|
|
"max_position_embeddings": 8192,
|
|
"model_type": "qwen",
|
|
"no_bias": true,
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 24,
|
|
"onnx_safe": null,
|
|
"rotary_emb_base": 10000,
|
|
"rotary_pct": 1.0,
|
|
"scale_attn_weights": true,
|
|
"seq_length": 8192,
|
|
"tie_word_embeddings": false,
|
|
"tokenizer_class": "QWenTokenizer",
|
|
"transformers_version": "4.32.0",
|
|
"use_cache": true,
|
|
"use_dynamic_ntk": true,
|
|
"use_flash_attn": "auto",
|
|
"use_logn_attn": true,
|
|
"vocab_size": 151936
|
|
} |