Instructions to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16
# Run inference directly in the terminal:
llama cli -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16
# Run inference directly in the terminal:
llama cli -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16
# Run inference directly in the terminal:
./llama-cli -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16

Use Docker

docker model run hf.co/shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16

LM Studio
Jan
Ollama
How to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with Ollama:
```
ollama run hf.co/shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16
```

Unsloth Studio

How to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw to start chatting

Docker Model Runner
How to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with Docker Model Runner:
```
docker model run hf.co/shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16
```

Lemonade

How to use shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shivvamm/Meta-Llama-3.1-8B_16bit_indianlaw:F16

Run and chat with the model

lemonade run user.Meta-Llama-3.1-8B_16bit_indianlaw-F16

List all available models

lemonade list

Atomic Chat

Model Card

Legal LLM (Fine-Tuned on Indian Supreme Court Synthetic Q&A)

Developed by: Shivam Pandey (shivvamm)
License: apache-2.0
Finetuned from: unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit

This model is a fine-tuned LLaMA-3.1-8B version optimized using Unsloth for high-speed training and inference.
It was trained on a synthetic legal Q&A dataset derived from Indian Supreme Court case data, enabling the model to reason over legal facts, summarize judgments, and answer domain-specific legal queries.

Training was conducted using the Hugging Face TRL library with Unsloth’s accelerated training pipeline, achieving ~2× faster fine-tuning compared to standard methods.

📘 Training Dataset

The training data consists of:

Synthetic legal questions and answers generated from publicly available Supreme Court of India judgment texts.
Structured Q&A style conversation format.
Emphasis on:
- Case summaries
- Legal principles
- Interpretations
- Procedural details
- Outcome classification

No private or confidential data was used.

🧠 Model Capabilities

The model has been evaluated on test samples from the synthetic dataset and performs reliably on:

Answering legal domain questions
Summarizing court judgments
Explaining legal concepts in simple language
Classifying legal issues
Extracting key principles from case texts

⚡ Performance

Initial testing shows:

Strong understanding of legal terminology
Accurate reasoning within the context of Supreme Court judgments
Smooth conversational and structured Q&A performance
Improved logical consistency after fine-tuning

Further benchmarking (e.g., LawBench, Indian legal QA datasets) is planned.

🚀 Fine-Tuning Details

Framework: Unsloth + Hugging Face TRL
Technique: PEFT / LoRA
Precision: 4-bit (bnb-4bit)
Training Speed: ~2× faster with Unsloth acceleration
Training Style: Instruction-tuned Q&A format

🗂 Use Cases

Legal research assistance
Court judgment summarization
Law student Q&A assistant
Domain-specific legal reasoning
Automated drafting helpers (non-advisory)

⚠️ Limitations & Disclaimer

The model does not provide real legal advice.
Outputs may contain inaccuracies and should not be used for professional legal decision-making.
The dataset includes synthetically generated labels, which may introduce bias or hallucinations.

❤️ Built With

This model was trained using:

Downloads last month: 19

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support