Indian Law Assistant 🏛️
A fine-tuned version of TinyLlama-1.1B on Indian legal data including IPC, CrPC, Constitution and Supreme Court judgments.
Model Details
- Base Model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
- Fine-tuning Method: LoRA (rank=8)
- Training Data: 20,198 Indian legal Q&A pairs
- Epochs: 2
- Final Training Loss: 0.96
Training Data Sources
- Indian Constitution Q&A (4,082 records)
- CrPC Q&A (8,194 records)
- IPC Q&A (2,267 records)
- IndicLegalQA Supreme Court Cases (10,002 records)
- IPC Sections (444 records)
How to Use
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
model = PeftModel.from_pretrained(model, "Sameer0904/indian-law-tinyllama")
tokenizer = AutoTokenizer.from_pretrained("Sameer0904/indian-law-tinyllama")
prompt = """<|system|>You are a helpful Indian legal assistant.</s>
<|user|>What is IPC Section 302?</s>
<|assistant|>"""
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Limitations
- Small model (1.1B) may hallucinate sometimes
- Not a substitute for professional legal advice
- Best for educational purposes only
Developer
- Sameer — AI/ML Enthusiast
- Downloads last month
- 42
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Sameer0904/indian-law-tinyllama
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0