---
base_model: google/gemma-3-1b-it
tags:
- gemma-3
- text-generation
- reasoning
---

# gemma-3-1b-it-reasoning

This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) optimized for step-by-step reasoning tasks using the [nohurry/Opus-4.6-Reasoning-3000x-filtered](https://huggingface.co/datasets/nohurry/Opus-4.6-Reasoning-3000x-filtered) dataset.

### Model Description
- **Developed by:** the81coder
- **Model type:** Gemma 3
- **Language(s):** English
- **License:** Gemma Terms of Use
- **Fine-tuned from model:** google/gemma-3-1b-it

### Training Procedure
The model was fine-tuned using QLoRA with the following configurations:
- **Learning Rate:** 1e-5
- **Batch Size:** 1 (with 4 accumulation steps)
- **Optimizer:** AdamW
- **Precision:** bfloat16
- **Target Modules:** q_proj, v_proj, k_proj, o_proj


### Usage
You can use this model with the `transformers` library:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = 'the81coder/gemma-3-1b-it-reasoning'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map='auto'
)
```