---
license: mit
library_name: transformers
pipeline_tag: text-generation
tags:
- designcoder
- ui-generation
- front-end
- html
- css
- javascript
- code-generation
- full-sft
---

# DesignCoder

Checkpoint collection for **DesignCoder**, a family of full-parameter SFT models for UI design
research and end-to-end HTML/CSS/JavaScript implementation.

Each subfolder in this repository is a self-contained, directly loadable checkpoint.

## Naming convention

```
designcoder_{basemodel}_{size}_{optimizer}_bs{global_batch}[_{extra_axes}]_step{global_step}
```

- `basemodel` / `size`: base model family and parameter scale
- `optimizer`: `muon` or `adamw`
- `bs`: global batch size (`per_device × grad_accum × world_size`)
- `extra_axes`: any hyper-parameter that deviates from the default recipe, e.g. `wd0.05`
  (weight decay, default 0.0) or `ep20` (epochs, default 2)
- `step`: trainer `global_step` of the exported weights

## Checkpoints

| Subfolder | Base model | Optimizer | LR | Global batch | Epochs | Weight decay | Step | Notes |
|---|---|---|---|---|---|---|---|---|
| `designcoder_qwen3.5_4b_muon_bs32_step1900` | Qwen3.5-4B | Muon | 1e-5 | 32 | 2 | 0.0 | 1900 | smallest release |
| `designcoder_qwen3.5_9b_muon_bs16_step3800` | Qwen3.5-9B | Muon | 1e-5 | 16 | 2 | 0.0 | 3800 | optimizer ablation (Muon arm) |
| `designcoder_qwen3.5_9b_adamw_bs16_step3800` | Qwen3.5-9B | AdamW | 2e-5 | 16 | 2 | 0.0 | 3800 | optimizer ablation (AdamW arm) |
| `designcoder_qwen3.6_27b_adamw_bs32_step1900` | Qwen3.6-27B | AdamW | 1e-5 | 32 | 2 | 0.0 | 1900 | largest release |

## Shared training setup

- Objective: full-parameter supervised fine-tuning (no LoRA / adapters)
- Dataset: `designcoder_sft_v2_train`, 41,287 ShareGPT-format records
- Chat template: `qwen3_5` with thinking enabled
- Context length: 32,768
- Sequence packing: enabled, with neat packing (no cross-sample attention)
- LR schedule: cosine, warmup ratio 0.1

## Usage

```python
from transformers import AutoModelForCausalLM, AutoProcessor

repo = "xingxm/DesignCoder"
subfolder = "designcoder_qwen3.5_4b_muon_bs32_step1900"

model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(repo, subfolder=subfolder)
```

To download a single checkpoint only:

```bash
hf download xingxm/DesignCoder --include "designcoder_qwen3.5_4b_muon_bs32_step1900/*" --local-dir ./DesignCoder
```

## Provenance

Each subfolder additionally ships `trainer_state.json` / `trainer_log.jsonl` (and
`training_loss.png` where available) so that the loss curve and exact step schedule of the run
can be recovered from the checkpoint itself.