Update README.md

README.md

@@ -41,6 +41,38 @@ Format your prompt as
 ```
 where `instruction` is your query.
 
+
+Here's a full-fledged example:
+
+```
+import torch
+import transformers
+
+model_name_or_path = "lxuechen/phi-2-sft"
+
+model: transformers.PreTrainedModel = transformers.AutoModelForCausalLM.from_pretrained(
+    model_name_or_path,
+    low_cpu_mem_usage=True,
+    device_map="auto",
+    trust_remote_code=True,
+    torch_dtype=torch.float16
+)
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name_or_path)
+
+input_text = "### Human: Give me a good recipe for a chinese dish\n\n### Assistant:"
+
+outputs = model.generate(
+    tokenizer(input_text, return_tensors="pt").to(model.device), max_length=1024,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id,
+    max_new_tokens=1024
+)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
 ## Training
 
 The model was fine-tuned on a sanitized version of the single-turn OASST dataset linked above.