Update README.md

README.md

@@ -36,6 +36,45 @@ Total Training Duration：69h18m17s
 }
 ```
 
+### Sample inference code
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+torch.random.manual_seed(0)
+model_id = "/home/intelisu/models/weight/phi3/Phi-3-medium-128k-instruct/"
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="cuda", 
+    torch_dtype="auto", 
+    trust_remote_code=True, 
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [
+    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
+    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
+    {"role": "user", "content": "Write a python code to train llm mode by lora and sft ?"},
+]
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+)
+
+generation_args = {
+    "max_new_tokens": 4096,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+output = pipe(messages, **generation_args)
+print(output[0]['generated_text'])
+
+```
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: