---
license: apache-2.0
base_model: unsloth/Qwen3-0.6B
tags:
  - fine-tuned
---

# Qwen3-0.6B_essobi-lima-2026-01-28-v1

This model was fine-tuned from [unsloth/Qwen3-0.6B](https://huggingface.co/unsloth/Qwen3-0.6B).

## Training Details

- **Base Model:** unsloth/Qwen3-0.6B
- **Training Method:** LoRA (PEFT)
- **Epochs:** 3
- **Learning Rate:** 1e-5
- **LoRA Rank:** 128
- **LoRA Alpha:** 128

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("essobi/Qwen3-0.6B_essobi-lima-2026-01-28-v1")
tokenizer = AutoTokenizer.from_pretrained("essobi/Qwen3-0.6B_essobi-lima-2026-01-28-v1")
```