Upload 4 files

start.sh

@@ -15,10 +15,11 @@ vllm serve unsloth/llama-3-8b-Instruct-bnb-4bit \
   --quantization bitsandbytes \
   --load-format bitsandbytes \
   --dtype half \
-  --enforce-eager &
+  --enforce-eager \
+  --max-model-len 8192 &
 
 # Wait to ensure the vLLM server is fully started (adjust if needed)
 sleep 10
 
 # Start the Gradio application using python3
-python3 app.py
+python3 app.py