Update README.md

README.md

@@ -1,3 +1,44 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+Below is the reference code for inference. First load the tokenizer and the model.
+
+```
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("KLGR123/WEPO-mistral-7b", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("KLGR123/WEPO-mistral-7b", trust_remote_code=True).to('cuda:0')
+```
+
+Run a test-demo with random input.
+
+```
+messages = [
+    {"role": "system", "content": "You are a web navigation intelligence who interacts with webpage environments to achieve human user intent."},
+    {"role": "user", "content": "Who are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=128,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.2,
+    top_p=0.9,
+)
+
+response = outputs[0][input_ids.shape[-1]:]
+output = tokenizer.decode(response, skip_special_tokens=True)
+output
+```