初始化项目,由ModelHub XC社区提供模型

Model: casperhansen/deepseek-r1-distill-llama-8b-awq
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-30 21:28:17 +08:00
commit 8f0f3c26be
10 changed files with 2936 additions and 0 deletions

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": 128001,
"transformers_version": "4.47.1",
"use_cache": false
}