Update README.md

README.md

@@ -22,6 +22,41 @@ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https
 
 This model has been fine tuned with mosaicml/instruct-v3 dataset with 2 epoch only. Mainly this model is useful for RAG based application
 
+## How to use?
+from peft import PeftModel
+
+# load the base model
+model_path = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+tokenizer=AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype = torch.bfloat16,
+    device_map = "auto",
+    trust_remote_code = True
+)
+#load the adapter 
+model_peft = PeftModel.from_pretrained(model, "azam25/TinyLlama_instruct_generation")
+
+messages = [{
+    "role": "user",
+    "content": "Act as a gourmet chef. I have a friend coming over who is a vegetarian. \
+    I want to impress my friend with a special vegetarian dish. \
+    What do you recommend? \
+    Give me two options, along with the whole recipe for each"
+}]
+
+def generate_response(message, model):
+  prompt = tokenizer.apply_chat_template(messages, tokenize=False)
+  encoded_input = tokenizer(prompt,  return_tensors="pt", add_special_tokens=True)
+  model_inputs = encoded_input.to('cuda')
+  generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True, pad_token_id=tokenizer.eos_token_id)
+  decoded_output = tokenizer.batch_decode(generated_ids)
+  return decoded_output[0]
+
+response = generate_response(messages, model)
+print(response)
+
+
 ## Intended uses & limitations
 
 More information needed