---
license: apache-2.0
language:
- en
library_name: peft
base_model: Qwen/Qwen3-8B
tags:
- qwen3
- qwen3-8b
- lora
- peft
- code-style
- android
- kotlin
- unsloth
- qlora
- llama-cpp
- gguf
- fine-tuning
pipeline_tag: text-generation
---

# Code Style LoRA for Qwen3-8B

A **QLoRA adapter** fine-tuned on 201 Android project source files to teach
Qwen3-8B a specific coding style. Designed for llama.cpp (via GGUF conversion)
or HuggingFace Transformers + PEFT.

## What this adapter does

- Learns **Kotlin** coding patterns: naming conventions, import ordering,
  brace style, comment density
- Captures Android architecture patterns: ViewModel, Repository, Room DB,
  Retrofit networking
- Embeds dependency injection style (Hilt)
- No unwanted boilerplate — trained to generate exactly the level of
  verbosity you use

## Training details

| Parameter | Value |
|---|---|
| Base model | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) |
| Method | QLoRA (4-bit NF4 via Unsloth) |
| LoRA rank | r=16, alpha=16 |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Training data | 201 source files from 2 Android projects |
| File types | Kotlin (169), Gradle KTS (18), XML resources (14) |
| Epochs | 3 |
| Sequence length | 2048 |
| Learning rate | 2e-4 (cosine scheduler) |
| Hardware | T4 GPU (16GB VRAM) via Google Colab |
| Framework | Unsloth + TRL SFTTrainer |

## Usage with Transformers + PEFT

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

model = PeftModel.from_pretrained(
    AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", device_map="auto"),
    "antiableofnormies/qwen3-8b-lora-android-dev",
)
tokenizer = AutoTokenizer.from_pretrained("antiableofnormies/qwen3-8b-lora-android-dev")
Usage with llama.cpp
python convert_lora_to_gguf.py     --base Qwen3-8B-Q4_K_M.gguf     --lora ./qwen3-style-lora/     --output style-adapter.gguf

llama-server -m Qwen3-8B-Q4_K_M.gguf     --lora style-adapter.gguf     --host 0.0.0.0 -ngl 99 --ctx-size 32768 --port 8080 --mlock

# Optional: merge into a standalone GGUF
llama-export-lora -m Qwen3-8B-Q4_K_M.gguf     --lora style-adapter.gguf     -o qwen3-code-style-merged.gguf
Intended use
This adapter is designed for a local coding assistant (opencode + llama.cpp)
that:
- Runs entirely on your machine (no API calls)
- Respects your existing code conventions
- Avoids unwanted boilerplate that cloud APIs tend to add
- Matches the patterns found in the training projects
Limitations
- Trained on a personal codebase — style may not generalize to unrelated
projects
- LoRA rank 16 captures high-level style (naming, structure) but not deep
domain knowledge
- Jetpack Compose UI code was explicitly excluded from training
- English-only code and comments