Add usage ex

README.md

@@ -6,4 +6,90 @@ base_model:
 - mistralai/Mistral-7B-v0.1
 tags:
 - legal
----
+---
+
+# reglab-rrc/mistral-rrc
+
+**Paper:** [AI for Scaling Legal Reform: Mapping and Redacting Racial Covenants in Santa Clara County]()
+
+
+## Usage
+
+Here is an example of how to use the model to find racial covenants in a page of text:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import re
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("reglab/mistral-rrc")
+model = AutoModelForCausalLM.from_pretrained("reglab/mistral-rrc")
+
+def format_prompt(document):
+    return f"""### Instruction:
+Determine whether the property deed contains a racial covenant. A racial covenant is a clause in a document that \
+restricts who can reside, own, or occupy a property on the basis of race, ethnicity, national origin, or religion. \
+Answer "Yes" or "No". If "Yes", provide the exact text of the relevant passage and then a quotation of the passage \
+with spelling and formatting errors fixed.
+
+### Input:
+{document}
+
+### Response:"""
+
+def parse_output(output):
+    answer_match = re.search(r"\[ANSWER\](.*?)\[/ANSWER\]", output, re.DOTALL)
+    raw_passage_match = re.search(r"\[RAW PASSAGE\](.*?)\[/RAW PASSAGE\]", output, re.DOTALL)
+    quotation_match = re.search(r"\[CORRECTED QUOTATION\](.*?)\[/CORRECTED QUOTATION\]", output, re.DOTALL)
+    
+    answer = answer_match.group(1).strip() if answer_match else None
+    raw_passage = raw_passage_match.group(1).strip() if raw_passage_match else None
+    quotation = quotation_match.group(1).strip() if quotation_match else None
+    
+    return {
+        "answer": answer == "Yes",
+        "raw_passage": raw_passage,
+        "quotation": quotation
+    }
+
+# Example usage
+document = "Your property deed text here..."
+prompt = format_prompt(document)
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=512)
+result = tokenizer.decode(outputs[0])
+parsed_result = parse_output(result)
+
+print(parsed_result)
+```
+
+The model was trained with the given input and output formats, so be sure to use them
+when performing inference.
+
+## Intended Use
+
+This model is designed to detect racial covenants in property deeds.
+
+## Training Data
+
+
+## Performance
+
+
+## Limitations
+
+
+## Ethical Considerations
+
+
+
+## Citation
+
+```
+@article{suranisuzgun2024,
+  title={AI for Scaling Legal Reform: Mapping and Redacting Racial Covenants in Santa Clara County},
+  author={Surani, Faiz and Suzgun, Mirac and Raman, Vyoma and Manning, Christopher D. and Henderson, Peter and Ho, Daniel E.},
+  journal={},
+  year={2024}
+}
+```

tokenizer_config.json

@@ -41,7 +41,6 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "tokenizer_file": "/scratch/users/faiz/hf_cache/models--reglab-rrc--mistral-rrc3.3/snapshots/18d20c079ee2a6b18567a9ff73e61281b6e6bf0e/tokenizer.json",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }