Instructions to use AISimplyExplained/Vakil-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AISimplyExplained/Vakil-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AISimplyExplained/Vakil-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AISimplyExplained/Vakil-7B")
model = AutoModelForCausalLM.from_pretrained("AISimplyExplained/Vakil-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AISimplyExplained/Vakil-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AISimplyExplained/Vakil-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISimplyExplained/Vakil-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AISimplyExplained/Vakil-7B

SGLang

How to use AISimplyExplained/Vakil-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AISimplyExplained/Vakil-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISimplyExplained/Vakil-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AISimplyExplained/Vakil-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISimplyExplained/Vakil-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AISimplyExplained/Vakil-7B with Docker Model Runner:
```
docker model run hf.co/AISimplyExplained/Vakil-7B
```

Vakil-7B Model Card

Model Description

Vakil-7B is a state-of-the-art language model fine-tuned on the AISimplyExplained/LegalReasoningIndianLaw dataset for specialization in the nuances and complexities of Indian law. It is designed to provide legal professionals, students, and researchers with insights and assistance in understanding legal documents and queries within the context of the Indian legal system.

Developed by Asmi Gulati and Bhuvi Jain, this tool aims to enhance the accessibility and analysis of legal texts, driving forward the digital transformation in the legal domain.

Model Specifications

Developed by: Asmi Gulati and Bhuvi Jain
Model type: Fine-tuned language model
Language(s) (NLP): English, with a focus on Indian legal terminology
License: MIT
Finetuned from model: transformers library model

Directions for Usage


!pip install "unsloth[colab_ampere] @ git+https://github.com/unslothai/unsloth.git"
!pip install "git+https://github.com/huggingface/transformers.git"

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AISimplyExplained/Vakil-7B")
model = AutoModelForCausalLM.from_pretrained("AISimplyExplained/Vakil-7B")

Intended Use

Vakil-7B is intended for direct use by legal professionals and researchers who need to interact with Indian legal text. It is designed to assist with legal research, drafting, and education by providing AI-driven analysis and insights.

Out-of-Scope Use

Vakil-7B is not designed to replace professional legal advice or to be used as a standalone decision-making tool. It should be used as an aid in the legal research and analysis process, not as the sole source of guidance.

Bias, Risks, and Limitations

Users should be aware of the inherent limitations of AI in interpreting legal text. Vakil-7B, while sophisticated, may not capture all nuances and should be used in conjunction with professional judgment.

Downloads last month: 214

Safetensors

Model size

7B params

Tensor type

F32

F16

AISimplyExplained
/

Vakil-7B