feat: add qwen 2.5 models for silicon flow (#3203)

### What problem does this PR solve? add qwen 2.5 models for silicon flow ### Type of change - [X] New Feature (non-breaking change which adds functionality)
infiniflow · Nov 5, 2024 · 7e89be5 · 7e89be5
1 parent b7b30c4
commit 7e89be5
Showing 1 changed file with 61 additions and 7 deletions.
diff --git a/conf/llm_factories.json b/conf/llm_factories.json
@@ -2017,6 +2017,60 @@
                     "max_tokens": 32768,
                     "model_type": "chat"
                 },
+                {
+                    "llm_name": "Qwen/Qwen2.5-72B-Instruct-128K",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 131072,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Qwen/Qwen2.5-72B-Instruct",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Qwen/Qwen2.5-7B-Instruct",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Qwen/Qwen2.5-14B-Instruct",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Qwen/Qwen2.5-32B-Instruct",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Qwen/Qwen2.5-Math-72B-Instruct",
+                    "tags": "LLM,CHAT,Math,4k",
+                    "max_tokens": 4096,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Qwen/Qwen2.5-Coder-7B-Instruct",
+                    "tags": "LLM,CHAT,FIM,Coder,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Pro/Qwen/Qwen2.5-7B-Instruct",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "Pro/Qwen/Qwen2.5-Coder-7B-Instruct",
+                    "tags": "LLM,CHAT,FIM,Coder,32k",
+                    "max_tokens": 32768,
+                    "model_type": "chat"
+                },
                 {
                     "llm_name": "01-ai/Yi-1.5-34B-Chat-16K",
                     "tags": "LLM,CHAT,16k",
@@ -2376,11 +2430,11 @@
             "llm": []
         },
         {
-      "name": "HuggingFace",
-      "logo": "",
-      "tags": "TEXT EMBEDDING",
-      "status": "1",
-      "llm": []
-    }
+            "name": "HuggingFace",
+            "logo": "",
+            "tags": "TEXT EMBEDDING",
+            "status": "1",
+            "llm": []
+        }
     ]
-}
+}