Update README.md

README.md

@@ -8,6 +8,11 @@ tags:
 - grpo
 - unsloth
 licence: license
+license: mit
+datasets:
+- axondendriteplus/legal-qna-dataset
+language:
+- en
 ---
 # llama-3.2-3B-GLR (GRPO Legal Reasoning)
 
@@ -15,6 +20,8 @@ This repository provides a Llama 3.2 3B model fine-tuned on a legal Q&A dataset
 
 ## Usage
 
+Download the files first, then run the below code in inference.py
+
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -34,7 +41,9 @@ What are the elements of a valid contract?
 <|start_header_id|>assistant<|end_header_id|>
 """
 
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+user_question = "What are the elements of a valid contract?"
+system_prompt = f"""{prompt} + {user_question}"""
+inputs = tokenizer(system_prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=256)
 response = tokenizer.decode(outputs[0])
 print(response)