初始化项目,由ModelHub XC社区提供模型
Model: stelterlab/DeepSeek-R1-Distill-Qwen-14B-AWQ Source: Original Platform
This commit is contained in:
37
config.json
Normal file
37
config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"_name_or_path": "/data/hf/models/models--deepseek-ai--DeepSeek-R1-Distill-Qwen-14B/snapshots/6453600843497f04e63f069049e92bf221d9e000",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 48,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"modules_to_not_convert": null,
|
||||
"quant_method": "awq",
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.47.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
Reference in New Issue
Block a user