support deepseek moe

2025-12-16 11:50:35 +08:00 · 2024-01-14 00:14:49 +08:00
parent d1a73fe26c
commit ca3933dc52
2 changed files with 16 additions and 0 deletions
--- a/src/llmtuner/extras/constants.py
+++ b/src/llmtuner/extras/constants.py
@@ -269,6 +269,21 @@ register_model_group(
 )


+register_model_group(
+    models={
+        "DeepseekMoE-16B-Base": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base"
+        },
+        "DeepseekMoE-16B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
+            DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat"
+        }
+    },
+    template="deepseek"
+)
+
+
 register_model_group(
    models={
        "Falcon-7B": {