File size: 1,110 Bytes
4658aaa f59a0a9 4658aaa 405556d 4658aaa 4e41480 4658aaa |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
{
"activation": "swiglu",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"QWenLMHeadModel"
],
"auto_map": {
"AutoConfig": "configuration_qwen.QWenConfig",
"AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
},
"attn_pdrop": 0.0,
"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-05,
"model_type": "qwen",
"n_embd": 4096,
"n_head": 32,
"n_layer": 32,
"n_positions": 6144,
"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": 2048,
"tie_word_embeddings": false,
"tokenizer_type": "QWenTokenizer",
"transformers_version": "4.31.0",
"use_cache": true,
"use_flash_attn": true,
"vocab_size": 151936,
"use_dynamic_ntk": true,
"use_logn_attn": true
}
|