Update README.md

README.md

@@ -52,4 +52,29 @@ It's test model. I hope I can reproduce a rl model like RL-Zero.
 
 This model is a mini-step.
 
-Thanks for evveryone in the open community.
+Thanks for evveryone in the open community.
+
+how to use:
+```
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model = LLM(
+    "Amu/t1-1.5B"
+)
+tok = AutoTokenizer.from_pretrained("simplescaling/s1-32B")
+
+stop_token_ids = tok("<|im_end|>")["input_ids"]
+
+sampling_params = SamplingParams(
+    max_tokens=32768,
+    min_tokens=0,
+    stop_token_ids=stop_token_ids,
+)
+
+prompt = "How many r in raspberry"
+prompt = "<|im_start|>system\nYou are t1, created by Amu. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n" + prompt + "<|im_end|>\n<|im_start|>assistant\n"
+
+o = model.generate(prompt, sampling_params=sampling_params)
+print(o[0].outputs[0].text)
+```