Quantizations of https://huggingface.co/Tesslate/WEBGEN-4B-Preview
Open source inference clients/UIs
Closed source inference clients/UIs
- LM Studio
- More will be added...
From original readme
Quickstart
Transformers
model_id = "Tesslate/WEBGEN-4B-Preview" 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
sglang
Tip: Lower temperature (e.g.,
0.4–0.6) yields stricter, cleaner markup. Raise it for more visual variety.
Inference Settings (suggested)
Prompts that work well
Quantization & VRAM (example)
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.
Training Summary (research preview)
- Base: Qwen/Qwen3-4B-Instruct
- 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