YOLO-7B-Qwen-Coder

A fine-tuned version of Qwen2.5-Coder-7B-Instruct specialized in diagnosing CLI errors and generating a single, precise bash fix command.

Part of the yolo-coder project — an automated CLI repair tool that wraps any command, catches failures, and fixes them locally using a local LLM.

---

What it does

Given a CLI error message and surrounding code context, the model outputs exactly one bare bash command to fix the problem. No explanation. No markdown. No backticks. Just the fix.

Input:  ModuleNotFoundError: No module named 'requests'
Output: pip install requests

Input:  IndexError: list index out of range  (line 7: print(items[2]))
Output: python3 yoco_replace.py app.py 7 'print(items[1])'

---

Model Details

Property	Value
Base model	Qwen/Qwen2.5-Coder-7B-Instruct
Fine-tune method	LoRA (MLX on Apple Silicon)
LoRA rank	8
LoRA scale	20.0
Layers trained	28
Training iterations	800
Learning rate	5e-6
Batch size	2 (grad accumulation × 4 = effective 8)
Max sequence length	1024
Training hardware	Apple Silicon M-series (16GB)
Final train loss	0.217
Final val loss	0.260

---

Training Data

Trained on a custom dataset of 2,250 CLI error/fix pairs covering:

• Python: SyntaxError, ImportError, ModuleNotFoundError, AttributeError, IndexError, KeyError, TypeError, ZeroDivisionError, PermissionError, FileNotFoundError
• pip: missing packages, --break-system-packages, hash mismatches, permissions
• Node.js: Cannot find module, MODULE_NOT_FOUND
• npm: ENOENT, ERESOLVE, EACCES
• TypeScript: TS2304, TS2339
• Docker: image not found, port conflicts, container name collisions, daemon not running
• Git: merge conflicts, detached HEAD, push rejected, not a repo
• Web frameworks: Next.js, FastAPI, Flask, Express
• Auth errors: JWT, OAuth, session issues
• Async/CORS errors

Format: ChatML with a strict system prompt enforcing single-command output.

90/10 train/validation split → 2025 train, 225 validation examples.

---

Files in this repo

File	Description
YOLO-7B-Qwen-q4.gguf	Q4_K_M quantized GGUF (~4.4GB) — recommended for Ollama
YOLO-7B-Qwen-finetuned.gguf	f16 GGUF (~14GB) — full quality, for requantization
safetensors/	fp16 HuggingFace safetensors — for further fine-tuning
adapter/	Raw LoRA adapter weights (MLX format)

---

Usage with Ollama

# Download the Modelfile
curl -O https://raw.githubusercontent.com/erdemozkan/yolo-coder/main/YOLO-MODEL-FILES/Modelfile-7B

# Pull the GGUF and register
ollama create yolo-7b -f Modelfile-7B

# Test it
ollama run yolo-7b "ModuleNotFoundError: No module named 'flask'"
# → pip install flask

---

Usage with yolo-coder

git clone https://github.com/erdemozkan/yolo-coder
cd yolo-coder
pip install -e .

# Use the 7B model
yoco --model yolo-7b python3 myapp.py

---

Usage with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "erdemozkan/YOLO-7B-Qwen-Coder"
tokenizer = AutoTokenizer.from_pretrained(model_id, subfolder="safetensors")
model = AutoModelForCausalLM.from_pretrained(model_id, subfolder="safetensors")

messages = [
    {"role": "system", "content": "You are a CLI repair tool. Output ONLY a single bare bash command to fix the error. No explanation. No markdown. No backticks."},
    {"role": "user", "content": "ModuleNotFoundError: No module named 'requests'"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=64, temperature=0.1)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
# → pip install requests

---

Prompt Format (ChatML)

<|im_start|>system
You are a CLI repair tool. Output ONLY a single bare bash command to fix the error. No explanation. No markdown. No backticks.<|im_end|>
<|im_start|>user
{error message}
<|im_end|>
<|im_start|>assistant

---

Limitations

• Outputs a single command only — not suitable for multi-step fixes without a wrapper
• Trained on common CLI errors; rare or highly domain-specific errors will fall back to base model behavior
• Not a general coding assistant — use base Qwen2.5-Coder for that

---

License

Apache 2.0 — same as the base model.