Instructions to use abhinavsunil/lexai-gemma2b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abhinavsunil/lexai-gemma2b-lora with Transformers:

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

pipe = pipeline("text-generation", model="abhinavsunil/lexai-gemma2b-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("abhinavsunil/lexai-gemma2b-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abhinavsunil/lexai-gemma2b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abhinavsunil/lexai-gemma2b-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abhinavsunil/lexai-gemma2b-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abhinavsunil/lexai-gemma2b-lora

SGLang

How to use abhinavsunil/lexai-gemma2b-lora 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 "abhinavsunil/lexai-gemma2b-lora" \
    --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": "abhinavsunil/lexai-gemma2b-lora",
		"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 "abhinavsunil/lexai-gemma2b-lora" \
        --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": "abhinavsunil/lexai-gemma2b-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abhinavsunil/lexai-gemma2b-lora with Docker Model Runner:
```
docker model run hf.co/abhinavsunil/lexai-gemma2b-lora
```

lexai-gemma2b-lora / README.md

abhinavsunil

Update README.md

456757f verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

1.24 kB

metadata

license: apache-2.0
tags:
  - gemma
  - legal
  - indian-law
  - fine-tuned
  - LoRA
  - transformers
  - text-generation

LexAI - Gemma-2B (LoRA Fine-Tuned for Indian Legal Instruction)

This is a LoRA fine-tuned version of Google's Gemma-2B model on a custom dataset of Indian legal instructions, writ petitions, bail applications, and more.

The model is part of the LexAI initiative — a lightweight legal language model assistant that can be integrated with voice systems like Whisper ASR and Coqui TTS.

🧠 Model Details

Base Model: google/gemma-2b
LoRA Config:
- r=8
- alpha=16
- dropout=0.05
- Target Modules: ["q_proj", "v_proj"]
Quantization: 8-bit (via bitsandbytes)
Fine-Tuned Using: Hugging Face PEFT + Transformers
Training Epochs: 3
Batch Size: 2 (accumulated over 4 steps)
Device: Google Colab T4 (12GB VRAM)

📚 Training Data

Custom JSONL dataset with 1,000+ legal examples formatted like:

### Instruction:
What is a bail application?

### Input:

### Response:
A bail application is a request made by a defendant seeking release from custody while the case is pending...