seeyon-sii-27b-lora

LoRA adapter for Qwen/Qwen3.8-27B (revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0) that turns English or Chinese UI requests into OpenUI Lang programs for the built-in OpenUI component library. Output is a bare program (no Markdown fences, no explanation) that starts with root = Stack(...).

Files

File	Purpose
adapter_model.safetensors, adapter_config.json	PEFT LoRA weights (r = 16) for the language model only
system-prompt.txt	Required system prompt for English requests
system-prompt-zh.txt	Required system prompt for Chinese requests (same rules plus Chinese UI-text instructions)

Required settings

• System prompt: send the full contents of system-prompt.txt (or system-prompt-zh.txt) as the system message on every request. The adapter relies on it for component signatures; do not shorten it.
• Thinking off: pass enable_thinking: false to the chat template.
• Context: the prompt is about 7.1k tokens before the request; allow at least 12k tokens of context.
• Decoding: greedy (temperature 0) and max_tokens around 2048.
• Follow-up edits: keep earlier turns in messages. The model returns a complete replacement program, not a diff.

Serve with vLLM

vllm serve Qwen/Qwen3.8-27B --revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0 \
  --max-model-len 20480 --limit-mm-per-prompt '{"image":0,"video":0}' \
  --enable-lora --max-lora-rank 16 --lora-modules openui=SeeyonAI/seeyon-sii-27b-lora

from pathlib import Path
from openai import OpenAI

system = Path('system-prompt.txt').read_text()
client = OpenAI(base_url='http://localhost:8000/v1', api_key='EMPTY')
reply = client.chat.completions.create(
    model='openui',
    messages=[
        {'role': 'system', 'content': system},
        {'role': 'user', 'content': 'Show a card titled Weekly sales with a bar chart: Mon 12, Tue 18, Wed 9.'},
    ],
    temperature=0,
    max_tokens=2048,
    extra_body={'chat_template_kwargs': {'enable_thinking': False}},
)
print(reply.choices[0].message.content)

On RTX PRO 6000 / other sm_120 GPUs with vLLM 0.30, set VLLM_USE_FLASHINFER_SAMPLER=0.

Use with Transformers + PEFT

from pathlib import Path
import torch
from peft import PeftModel
from transformers import AutoModelForImageTextToText, AutoTokenizer

base_id, rev = 'Qwen/Qwen3.8-27B', '1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0'
tokenizer = AutoTokenizer.from_pretrained(base_id, revision=rev)
model = AutoModelForImageTextToText.from_pretrained(base_id, revision=rev, dtype=torch.bfloat16, device_map='auto')
model = PeftModel.from_pretrained(model, 'SeeyonAI/seeyon-sii-27b-lora')

messages = [
    {'role': 'system', 'content': Path('system-prompt-zh.txt').read_text()},
    {'role': 'user', 'content': '显示一张卡片：本周订单 128 单，较上周增长 12%。'},
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False, return_tensors='pt', return_dict=True).to(model.device)
output = model.generate(**inputs, max_new_tokens=2048, do_sample=False)
print(tokenizer.decode(output[0, inputs['input_ids'].shape[1]:], skip_special_tokens=True))

Install flash-linear-attention and causal-conv1d; without them, the model's linear-attention layers fall back to slow PyTorch code. To merge the adapter into the base weights, use model.merge_and_unload(); this needs about 55 GB of disk for the merged copy.

Render the output

Parse and render programs with the OpenUI SDK versions the prompt was generated from: @openuidev/react-ui@0.18.0, @openuidev/react-lang@1.0.0, @openuidev/lang-core@1.0.0 (openuiLibrary). Validate before rendering, and treat form submissions and buttons as requests sent back to the assistant, not as completed backend actions.

Scope

• Covers the built-in openuiLibrary components, including static layouts and local reactive features (bindings, conditional visibility, modals, @Set/@Reset, @Count/@Sum/@Avg/@Filter/@Sort).
• Not covered: Query/Mutation/@Run tool integrations, incremental patch output, or custom component libraries.
• Outputs can still occasionally fail schema validation, for example when chart label and value counts differ. Always parse with the SDK before display.