Instructions to use tahsinahsen/birag-gemma4-e2b-response-only-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use tahsinahsen/birag-gemma4-e2b-response-only-lora with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("tahsinahsen/birag-gemma4-e2b-response-only-lora") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Unsloth Desktop
- MLX LM
How to use tahsinahsen/birag-gemma4-e2b-response-only-lora with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "tahsinahsen/birag-gemma4-e2b-response-only-lora"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "tahsinahsen/birag-gemma4-e2b-response-only-lora" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tahsinahsen/birag-gemma4-e2b-response-only-lora", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
BIRAG Gemma 4 E2B โ Response-only LoRA
This repository contains an Unsloth MLX LoRA adapter trained on top of
unsloth/gemma-4-E2B-it.
Training configuration
- Target: response_only
- Maximum sequence length: 8096
- LoRA rank: 16
- LoRA alpha: 16
- Epochs: 3
- Training records: 1790
- Validation records: 225
- Test records: 225
- Seed: 3407
Usage
This is a LoRA adapter, not a standalone merged model. It requires the
unsloth/gemma-4-E2B-it base model and an Unsloth-compatible MLX runtime.
Limitations
The model is intended for research and supportive guidance. It must not be treated as medical, psychological, or clinical advice.
Hardware compatibility
Log In to add your hardware
Quantized