Update README.md

README.md

@@ -168,13 +168,39 @@ You are a question answering assistant. Answer the question as truthful and help
 
 ## How to use
 
+### Huggingface
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Ensure CUDA is available
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+print(f"Using device: {device}")
+
+# Init Model
+model_path="openthaigpt/openthaigpt-1.0.0-7b-chat"
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.float16)
+model.to(device)
+
+# Prompt
+prompt = "สวัสดีครับ OpenThaiGPT"
+llama_prompt = f"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด<</SYS>>\n\n{prompt} [/INST]"
+inputs = tokenizer.encode(llama_prompt, return_tensors="pt")
+inputs = inputs.to(device)
+
+# Generate
+outputs = model.generate(inputs, max_length=512, num_return_sequences=1)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
 ### vLLM Engine for float16 model
 
 1. install VLLM (https://github.com/vllm-project/vllm)
 2. python -m vllm.entrypoints.api_server --model /path/to/model --tensor-parallel-size num_gpus
 3. run inference (CURL example)
 
-```
+```bash
 curl --request POST \
     --url http://localhost:8000/generate \
     --header "Content-Type: application/json" \