---
base_model: google/gemma-7b-it
tags:
  - adapter
  - lora
  - gemma
  - peft
  - causal-lm
---

# Flan V2 Adapter for Gemma-7B-IT

This is a LoRA adapter trained on **flan_v2**, compatible with `google/gemma-7b-it`.

## Usage

```python
from transformers import AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it")
model = PeftModel.from_pretrained(base, "RealSilvia/flan_v2-adapter")