req.txt

app.py

@@ -81,9 +81,9 @@ If the given question lacks the parameters required by the function, also point
         "content": json.dumps(convert_to_xlam_tool(tools))
     }]
 
-    model = AutoModelForCausalLM.from_pretrained("KishoreK/ActionGemma-9B", load_in_4bit=True, device_map="auto", use_cache=True,low_cpu_mem_usage=True )
+    model = AutoModelForCausalLM.from_pretrained("KishoreK/ActionGemma-9B", device_map="auto", use_cache=True,low_cpu_mem_usage=True )
     tokenizer = AutoTokenizer.from_pretrained("KishoreK/ActionGemma-9B")
-    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
     outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
     return tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)