GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wesjos
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
wesjos
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
Both screenshots are the bundled WebUI, model output rendered live — nothing hand-edited.
The trigger is a single system prompt, and it is already baked into chat_template.jinja in this repo — leave the system field empty and you get it for free; pass your own system and yours wins.
text
You are Mario-html. You are a helpful assistant who generates nice visual content.⚠️ It is a hard trigger. Without it the model falls back to ordinary 27B behaviour — long Markdown answers instead of a rendered page.
Output convention (from the training data; the WebUI keys off these class names):
html
<div class="ai-view"> <h2>Title</h2> <div class="summary"><p class="lead">…</p></div> <div class="card">…</div> <table class="modern-table">…</table></div>The chain of thought is kept intact — it was masked out of the loss, so the tune only changes how it writes, not how it thinks.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel BASE = "Qwen/Qwen3.8-27B"ADAPTER = "wesjos/Qwen3.8-27B-Mario-HTML-LoRA" bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True)tok = AutoTokenizer.from_pretrained(ADAPTER) # ships the modified chat templatemodel = AutoModelForCausalLM.from_pretrained(BASE, quantization_config=bnb, device_map="auto")model = PeftModel.from_pretrained(model, ADAPTER) msgs = [{"role": "user", "content": "Build a page introducing black holes"}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True, enable_thinking=True, reasoning_effort="low")inputs = tok(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=1.0, top_p=0.95, top_k=20)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))Prefer the runtime-mounted version? See wesjos/Qwen3.8-27B-Mario-HTML-LoRA-GGUF — same adapter, 21 MB, mounts on any Qwen3.8-27B GGUF without merging.
bash
cd webuipip install -r requirements.txtWEBUI_PORT=8798 API_URL=http://127.0.0.1:18080 MODEL_ALIAS=qwen3.8-27b ./run_webui.sh# → http://<host>:8798Left pane is the chat, right pane renders .ai-view / .card / .modern-table live. There's a reasoning: low / medium / high switch next to the input, an “Add Image” button (needs --mmproj on the backend), and an optional system-prompt override.
| Situation | Setting |
|---|---|
| Normal page | temperature 1.0 / top_p 0.95 / top_k 20 / min_p 0 |
| Thinking length | default medium (the template changed the default); low is shorter, xhigh will burn 20k+ tokens and truncate the page |
| HTML only, no reasoning | enable_thinking: false (under 90 tokens of thinking, but the format drifts occasionally) |
| Context | 131072 recommended (xhigh eats 8k–10k tokens per turn), max_tokens 16384 |
| Prompt (no format instructions) | Result |
|---|---|
Explain how neural networks learn, with a visual summary and a comparison table. | .ai-view + 5 cards + 3 tables |
Build a page introducing black holes | .ai-view + 13 cards + 2 tables + 7 h2 |
xhigh alone can consume 8k–10k tokens and a tight context slices the page mid-sentence (finish_reason=length).| File | What it is |
|---|---|
adapter_model.safetensors | the 42 MB LoRA adapter |
adapter_config.json | r16/α32, q/k/v/o targets |
chat_template.jinja | base template + the trigger system prompt, reasoning_effort default medium |
tokenizer.json, tokenizer_config.json | tokenizer |
webui/ | FastAPI + single-page frontend that renders the output live |
<div class="ai-view"> <h2>Title</h2> <div class="summary"><p class="lead">…</p></div> <div class="card">…</div> <table class="modern-table">…</table></div>import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel BASE = "Qwen/Qwen3.8-27B"ADAPTER = "wesjos/Qwen3.8-27B-Mario-HTML-LoRA" bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True)tok = AutoTokenizer.from_pretrained(ADAPTER) # ships the modified chat templatemodel = AutoModelForCausalLM.from_pretrained(BASE, quantization_config=bnb, device_map="auto")model = PeftModel.from_pretrained(model, ADAPTER) msgs = [{"role": "user", "content": "Build a page introducing black holes"}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True, enable_thinking=True, reasoning_effort="low")inputs = tok(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=1.0, top_p=0.95, top_k=20)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))cd webuipip install -r requirements.txtWEBUI_PORT=8798 API_URL=http://127.0.0.1:18080 MODEL_ALIAS=qwen3.8-27b ./run_webui.sh# → http://<host>:8798