chat_bot_server

Sleeping

gouravbhadraDev commited on 11 days ago

Commit

c7851f3

verified ·

1 Parent(s): e6978bd

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -7,6 +7,7 @@ app = FastAPI()
 qwen3_gguf_llm = Llama.from_pretrained(
     repo_id="unsloth/Qwen3-0.6B-GGUF",
     filename="Qwen3-0.6B-UD-Q8_K_XL.gguf",
 )
 class PromptRequest(BaseModel):

 qwen3_gguf_llm = Llama.from_pretrained(
     repo_id="unsloth/Qwen3-0.6B-GGUF",
     filename="Qwen3-0.6B-UD-Q8_K_XL.gguf",
+    n_threads=-1
 )
 class PromptRequest(BaseModel):