Instructions to use gazam/LegalEase_IndianConsumerLaw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gazam/LegalEase_IndianConsumerLaw with Transformers:

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

pipe = pipeline("text-generation", model="gazam/LegalEase_IndianConsumerLaw")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gazam/LegalEase_IndianConsumerLaw", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gazam/LegalEase_IndianConsumerLaw with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/gazam/LegalEase_IndianConsumerLaw

SGLang

How to use gazam/LegalEase_IndianConsumerLaw 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 "gazam/LegalEase_IndianConsumerLaw" \
    --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": "gazam/LegalEase_IndianConsumerLaw",
		"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 "gazam/LegalEase_IndianConsumerLaw" \
        --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": "gazam/LegalEase_IndianConsumerLaw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gazam/LegalEase_IndianConsumerLaw with Docker Model Runner:
```
docker model run hf.co/gazam/LegalEase_IndianConsumerLaw
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

LegalEase_IndianConsumerLaw

Model Details

Model Description

LegalEase_IndianConsumerLaw is a fine-tuned model designed to assist in answering legal questions related to Indian consumer laws. It is based on Mistral-7B and optimized for structured legal Q&A, consumer rights explanations, and legal text interpretation.

Developed by: Gulfarogh Azam
Model type: Causal Language Model (LLM)
Language(s): English (with a focus on Indian legal terminology)
Finetuned from: mistralai/Mistral-7B-v0.1
Trained on: The Consumer Protection Act, 2019, India.

Model Sources

Repository: Hugging Face Model Repo

Uses

Direct Use

Legal professionals, researchers, and individuals can query the model for Indian consumer law-related information.
Useful for understanding legal provisions and consumer rights.

Downstream Use

Can be integrated into legal chatbots or AI-powered legal assistance tools.

Out-of-Scope Use

Not a replacement for legal advice from a qualified lawyer.
May not cover state-specific regulations.
Should not be used for non-legal inquiries.

Bias, Risks, and Limitations

Bias

The model has been trained on a limited dataset, which may introduce biases.
Responses may not always align with the latest amendments in law.

Risks

May generate incorrect or outdated legal interpretations.
Does not account for regional variations in legal practice.

Recommendations

Users should cross-check critical legal information with official sources before making any decisions.

How to Use the Model

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "gazam/LegalEase_IndianConsumerLaw"

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained(repo_id)
tokenizer = AutoTokenizer.from_pretrained(repo_id)

# Generate a response
input_text = "What are my rights under the Consumer Protection Act?"
inputs = tokenizer(input_text, return_tensors="pt")
output = model.generate(**inputs, max_length=256)

print(tokenizer.decode(output[0], skip_special_tokens=True))

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for gazam/LegalEase_IndianConsumerLaw

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(947)

this model