Qwen-7B-QAnything / config.json
Zihui Ren
upload models
578225f
raw
history blame
1.26 kB
{
"_name_or_path": "model_repos/Qwen-7B-QAnything/",
"activation": "swiglu",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"QWenLMHeadModel"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "configuration_qwen.QWenConfig",
"AutoModel": "modeling_qwen.QWenLMHeadModel",
"AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
},
"bf16": false,
"bias_dropout_fusion": true,
"bos_token_id": 151643,
"embd_pdrop": 0.1,
"eos_token_id": 151643,
"ffn_hidden_size": 22016,
"fp16": false,
"initializer_range": 0.02,
"kv_channels": 128,
"layer_norm_epsilon": 1e-06,
"model_type": "qwen",
"n_embd": 4096,
"n_head": 32,
"n_inner": null,
"n_layer": 32,
"n_positions": 8192,
"no_bias": true,
"onnx_safe": null,
"padded_vocab_size": 151936,
"params_dtype": "torch.bfloat16",
"pos_emb": "rotary",
"resid_pdrop": 0.1,
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"scale_attn_weights": true,
"seq_length": 8192,
"tie_word_embeddings": false,
"tokenizer_type": "QWenTokenizer",
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"use_cache": true,
"use_dynamic_ntk": true,
"use_flash_attn": true,
"use_logn_attn": true,
"vocab_size": 151936
}