quocvibui/rhino-coder-7b-lora

Rhino Coder 7B — LoRA Adapter

A LoRA adapter for Qwen2.5-Coder-7B-Instruct, fine-tuned for Rhino3D Python scripting — generating correct rhinoscriptsyntax and RhinoCommon code from natural language instructions.

This is the standalone LoRA adapter (~660 MB). For the full fused model, see rhino-coder-7b.

Usage

With MLX (Apple Silicon)

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load(
    "Qwen/Qwen2.5-Coder-7B-Instruct",
    adapter_path="quocvibui/rhino-coder-7b-lora"
)

messages = [
    {"role": "system", "content": "You are an expert Rhino3D Python programmer. Write clean, working scripts using rhinoscriptsyntax and RhinoCommon. Include all necessary imports. Only output code, no explanations unless asked."},
    {"role": "user", "content": "Create a 10x10 grid of spheres with radius 0.5"},
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
output = generate(model, tokenizer, prompt=prompt, max_tokens=1024)
print(output)

As an OpenAI-compatible server

mlx_lm server \
    --model Qwen/Qwen2.5-Coder-7B-Instruct \
    --adapter-path quocvibui/rhino-coder-7b-lora \
    --port 8080

Adapter Details

Parameter	Value
LoRA rank	8
LoRA scale	20.0
LoRA dropout	0.0
LoRA layers	16 / 28
Adapter size	~660 MB

Training Details

Parameter	Value
Base model	Qwen2.5-Coder-7B-Instruct (4-bit)
Batch size	1
Learning rate	1e-5
Optimizer	Adam
Max sequence length	2,048
Iterations	9,108 (2 epochs)
Validation loss	0.184
Training time	~1.2 hours on M2 Max

Dataset

5,060 instruction-code pairs for Rhino3D Python scripting:

Source	Count
RhinoCommon API docs	1,355
RhinoScriptSyntax source	926
Official samples	93
Synthetic generation	187
Backlabeled GitHub	1

Links

• GitHub: rhino3d-SLM
• Fused model: rhino-coder-7b
• Base model: Qwen2.5-Coder-7B-Instruct