Update README.md

README.md

@@ -1,5 +1,36 @@
----
-license: other
-license_name: '-'
-license_link: https://ai.meta.com/llama/license
----
+---
+license: other
+license_name: '-'
+license_link: https://ai.meta.com/llama/license
+---
+
+```python
+import transformers
+import torch
+
+# 1. Load Model & Tokenizer
+model_id = "XXX/MedCEG"
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
+model = transformers.AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+# 2. Define Input
+question = "A 78-year-old Caucasian woman presented with..."
+suffix = "\nPut your final answer in \\boxed{}."
+messages = [{"role": "user", "content": question + suffix}]
+
+# 3. Generate
+input_ids = tokenizer.apply_chat_template(
+    messages, 
+    add_generation_prompt=True, 
+    return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(input_ids, max_new_tokens=8196, do_sample=False)
+decoded_response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
+
+print(decoded_response)
+```