Update start.sh

start.sh

@@ -11,11 +11,7 @@ export USER_AGENT="vllm_huggingface_space"
 vllm serve unsloth/llama-3-70b-Instruct-bnb-4bit \
   --enable-auto-tool-choice \
   --tool-call-parser llama3_json \
-  --chat-template examples/tool_chat_template_llama3.1_json.jinja \
-  --quantization bitsandbytes \
-  --load-format bitsandbytes \
-  --gpu_memory_utilization 0.9 \
-  --enforce-eager &
+  --chat-template examples/tool_chat_template_llama3.1_json.jinja &
 
 # Wait to ensure the vLLM server is fully started (adjust if needed)
 sleep 10