fix

llm_func.py

@@ -4,10 +4,9 @@ model = Llama.from_pretrained(repo_id="tensorblock/SmolLM-135M-Instruct-GGUF",fi
 
 
 def mdl(input):
-	print(query)
-	start = time.time()
-    output = model(
-    prompt=f"""<|im_start|>system
+    print(input)
+    start = time.time()
+    output = model(prompt=f"""<|im_start|>system
      You are a helpful chatbot.<|im_end|>
      <|im_start|>user
      {input}<|im_end|>""",
@@ -17,6 +16,6 @@ def mdl(input):
     echo=False,
     stop=["#"])
     end = time.time()
-	total_time = end - start
-	print(f"Execution time: {total_time:.2f} seconds")
+    total_time = end - start
+    print(f"Execution time: {total_time:.2f} seconds")
     return output["choices"][0]["text"].replace('\nassistant\n','')

requirements.txt

@@ -1,4 +1,5 @@
 fastapi
 uvicorn
 llama-cpp-python==0.3.6 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
-huggingface
+huggingface
+huggingface-hub