WEBGEN-OSS-20B
A web-only generator that turns one prompt into clean, responsive HTML/CSS/Tailwind. Small enough for laptops; opinionated for consistent, modern layouts.
<span class="pill">Open weights</span>
<span class="pill">Web-only bias</span>
<span class="pill">Mobile-first output</span>
<span class="pill">No external JS by default</span>
What it is
WEBGEN-OSS-20B focuses solely on generating production-lean websites. It prefers semantic HTML, sane spacing, and modern component blocks (hero, grids, pricing, FAQ).
Why
Small enough for local runs and fast iteration, while retaining strong structure/consistency for HTML/CSS/Tailwind output.
Quickstart
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer import torchmodel_id = "Tesslate/WEBGEN-OSS-20B" tok = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto" )
prompt = """Make a single-file landing page for 'LatticeDB'. Style: modern, generous whitespace, Tailwind, rounded-xl, soft gradients. Sections: navbar, hero (headline + 2 CTAs), features grid, pricing (3 tiers), FAQ accordion, footer. Constraints: semantic HTML, no external JS."""
inputs = tok(prompt, return_tensors="pt").to(model.device) out = model.generate(**inputs, max_new_tokens=2000, temperature=0.7, top_p=0.9) print(tok.decode(out[0], skip_special_tokens=True))
vLLM
vllm serve Tesslate/WEBGEN-OSS-20B \ --host 0.0.0.0 --port 8000 \ --max-model-len 65536 \ --gpu-memory-utilization 0.92
sglang
python -m sglang.launch_server \ --model-path Tesslate/WEBGEN-OSS-20B \ --host 0.0.0.0 --port 5000 \ --mem-fraction-static 0.94 \ --attention-backend flashinfer
Tip: Lower temperature (e.g.,
0.4–0.6) yields stricter, cleaner markup. Raise it for more visual variety.
Inference Settings (suggested)
| Param | Value | Notes |
|---|---|---|
temperature | 0.6 | Balance creativity & consistency (lower if quantized) |
top_p | 0.9 | Nucleus sampling |
top_k | 40 | Optional vocab restriction |
max_new_tokens | 1200–2500 | Single-file sites often fit < 1500 |
repetition_penalty | 1.1 | Reduces repetitive classes/markup |
Prompts that work well
Starter
Make a single-file landing page for "RasterFlow" (GPU video pipeline). Style: modern tech, muted palette, Tailwind, rounded-xl, subtle gradients. Sections: navbar, hero (big headline + 2 CTAs), logos row, features (3x cards), code block (copyable), pricing (3 tiers), FAQ accordion, footer. Constraints: semantic HTML, no external JS. Return ONLY the HTML code.
Design-strict
Use an 8pt spacing system. Palette: slate with indigo accents. Typography scale: 14/16/18/24/36/56. Max width: 1200px. Avoid shadows > md; prefer borders/dividers.
Quantization & VRAM (example)
| Format | Footprint | Notes |
|---|---|---|
| BF16 | 8.05 GB | Fastest, best fidelity |
| GGUF Q5_K_M | 2.89 GB | Great quality/size trade-off |
| GGUF Q4_K_M | 2.5 GB | Smallest comfortable for laptops |
Intended Use & Scope
- Primary: Generate complete, single-file websites (landing pages, marketing pages, simple docs) with semantic HTML and Tailwind classes.
- Secondary: Component blocks (hero, pricing, FAQ) for manual composition.
- Accessibility: adds headings/labels but ARIA coverage may need review.
- JS widgets: kept light unless explicitly requested in prompt.
- Curate prompts appropriately.
- When using third-party logos/assets, ensure you have rights or use open sources.
Training Summary (research preview)
- Objective: Tight web-only bias; reward semantic structure, spacing rhythm, and responsiveness.
- Data: Mixture of curated HTML/CSS/Tailwind snippets, component libraries, and synthetic page specs.
- Recipe: SFT with format constraints → instruction tuning → style/rhythm preference optimization.
- Context: effective ~64k; trained to keep default outputs within practical page length.
Example Outputs
Community
- Examples: uigenoutput.tesslate.com
- Discord: discord.gg/EcCpcTv93U
- Website: tesslate.com
“Why are good design models so expensive” — Tesslate Team
Citation
@misc{tesslate_webgen_oss_preview_2025,
title = {WEBGEN-OSS-20B: Design-first web generation},
author = {Tesslate Team},
year = {2025},
url = {https://huggingface.co/Tesslate/WEBGEN-OSS-20B}
}