Update llm/utils/config.py

llm/utils/config.py

@@ -15,20 +15,49 @@ config = {
         "load_in_8bit": True,
         "do_sample": True
     },
-    "LC_TinyLlama-1.1B-Chat-v1.0-GGUF": {
-        "model_url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q8_0.gguf",
-        "model_name": "tinyllama-1.1b-chat-v1.0.Q8_0.gguf.bin",
+    "HF_SmolLM135": {
+        "model": "HuggingFaceTB/SmolLM-135M-Instruct",
         "temperature": 0.5,
-        "max_tokens": 868,
-        "top_p": 0.8,
+        "max_new_tokens": 1024,
+        "top_k": 5,
+        "top_p":0.95,
+        "load_in_8bit": True,
+        "do_sample": True
+    },
+    "HF_SmolLM360": {
+        "model": "HuggingFaceTB/SmolLM-360M-Instruct",
+        "temperature": 0.5,
+        "max_new_tokens": 1024,
+        "top_k": 5,
+        "top_p":0.95,
+        "load_in_8bit": True,
+        "do_sample": True
+    },
+    "HF_SmolLM": {
+        "model": "HuggingFaceTB/SmolLM-1.7B-Instruct",
+        "temperature": 0.5,
+        "max_new_tokens": 1024,
         "top_k": 5,
+        "top_p":0.95,
+        "load_in_8bit": True,
+        "do_sample": True
     },
-    "LC_Phi-3-mini-4k-instruct-gguf": {
-        "model_url": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf",
-        "model_name": "Phi-3-mini-4k-instruct-gguf.bin",
+    "HF_Gemma2": {
+        "model": "google/gemma-2-2b",
         "temperature": 0.5,
-        "max_tokens": 868,
-        "top_p": 0.8,
+        "max_new_tokens": 1024,
         "top_k": 5,
-    }
+        "top_p":0.95,
+        "load_in_8bit": True,
+        "do_sample": True
+    },
+    "HF_Qwen2": {
+        "model": "Qwen/Qwen2-7B-Instruct",
+        "temperature": 0.5,
+        "max_new_tokens": 1024,
+        "top_k": 5,
+        "top_p":0.95,
+        "load_in_8bit": True,
+        "do_sample": True
+    },
 }