hf llm

backend.py

@@ -63,7 +63,7 @@ os.environ['TOKENIZERS_PARALLELISM'] = 'false'
 llm = HuggingFaceLLM(
     context_window=4096,
     max_new_tokens=256,
-    generate_kwargs={"temperature": 0.0, "do_sample": True},
+    generate_kwargs={"temperature": 0.1, "do_sample": True},
     system_prompt=system_prompt,
     tokenizer_name="meta-llama/Llama-2-7b-chat-hf",
     model_name="meta-llama/Llama-2-7b-chat-hf",