CoolFace
Modelpublic

tahsinahsen/birag-gemma4-e2b-response-only-lora

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes
Model Card

BIRAG Gemma 4 E2B – 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.