初始化项目，由ModelHub XC社区提供模型

Model: xd2010/Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma-1epo Source: Original Platform
2026-06-24 12:44:55 +08:00
commit 9d78c2114f
23 changed files with 160086 additions and 0 deletions
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.51.0",
+  "use_cache": false
+}