GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
caid-technologies
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
caid-technologies
Model Tree
Base
Qwen/Qwen3.5-9B
Fine-tuned
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
A plain-English request — one or two sentences.
A short document — a brief or notes in plain text/Markdown, pasted into the message:
text
<your request>--- ATTACHED DOCUMENT: brief.md ---<the document text>--- END DOCUMENT ---
A concept image — a hand-drawn sketch or product render, as a regular vision input.
Any combination works; prompt + brief + render is strongest. Convert PDFs, CAD files, or spreadsheets to text or an image first.
The model answers in JSON directly — no reasoning preamble to strip.
python
from unsloth import FastVisionModelREPO = "caid-technologies/parti-vision"model, tok = FastVisionModel.from_pretrained(REPO, load_in_4bit=False)FastVisionModel.for_inference(model)SYSTEM_PROMPT = ("You design maker/electronics products. Reply with one JSON object with exactly these ""10 keys: project, requirements, components, relationships, circuit, fabrication, ""instructions, appearance, image_generation_prompt, sourcing. Output only the JSON.")messages = [{"role": "system", "content": [{"type": "text", "text": SYSTEM_PROMPT}]},{"role": "user", "content": [{"type": "text", "text": "Design a USB desk lamp with touch dimming."}]},]text = tok.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)inputs = tok(text=text, return_tensors="pt").to("cuda")out = model.generate(**inputs, max_new_tokens=13000, do_sample=False, repetition_penalty=1.1)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
💡 Blueprints are long: keep max_new_tokens high and the repetition penalty on. To include an
image, add {"type": "image", "image": your_image} to the user content and pass images= to the
tokenizer.
🚀 Serving it for real? Use vLLM with guided_json constrained to the blueprint schema — it
takes valid-blueprint rates on unseen prompts from ~61% to ~97%.
Tested on 60 held-out examples and 42 fresh out-of-distribution prompts, scoring every output against the blueprint schema and semantic design checks:
| Valid-blueprint rate | In-distribution | Unseen realistic prompts |
|---|---|---|
| Plain decoding | ~67% | ~61% |
With guided_json (recommended) | ~83% | ~97% |
The stock base model scores 0% on the same tests.
Base model: Qwen/Qwen3.5-9B (Apache-2.0); this repo
is the fine-tune merged to 16-bit. Prefer the adapter? Use
caid-technologies/parti-vision-lora.
Output contract: one JSON object with exactly 10 top-level keys (
markdown
project, requirements, components, relationships, circuit, fabrication, instructions, appearance, image_generation_prompt, sourcing
schema.json + validate.py in the repo re-check any output.
Training: LoRA via Unsloth (r=16, α=16, bf16) over language attention+MLP layers, vision encoder frozen, then merged; 3 epochs, max seq 16384. Data: 150 synthetic records, each validated by the same schema + semantic gates, × 4 input variants (prompt / +brief / +sketch / +brief+render). Records authored by Claude Sonnet 5 and DeepSeek-V4-Pro; concept images by gpt-image-1.
Chat template: patched to default to enable_thinking=False (JSON directly) under
transformers, Unsloth, and vLLM; pass for a reasoning trace. If you
override the template in vLLM, re-add .
bibtex
@misc{parti_vision_base,title = {Parti-Vision Base: Qwen3.5-9B for multimodal hardware blueprint generation},author = {Caid Technologies},year = {2026},howpublished = {\url{https://huggingface.co/caid-technologies}}}
Built with Unsloth and 🤗 Transformers / PEFT / TRL.
enable_thinking=Truechat_template_kwargs={"enable_thinking": false}Evaluation (vLLM; strict parse = raw json.loads, no salvage; schema-valid = full pydantic
Product; gates = pin existence, sourcing arithmetic, phase order):
In-distribution, 60 held-out examples:
| Metric | Fine-tuned — free | Fine-tuned — guided_json | Base Qwen3.5-9B |
|---|---|---|---|
| Strict JSON parse | 0.85 | 0.83 | 0.97 |
Schema-valid (Product) | 0.67 | 0.83 | 0.00 |
| Gates-clean | 0.40 | 0.48 | 0.00 |
| Prompt-echo fidelity | 0.82 | 0.82 | 0.00 |
Out-of-distribution, 42 fresh prompts (free decoding):
| kind | n | parse | schema |
|---|---|---|---|
| realistic paraphrase | 10 | 0.90 | 0.70 |
| new domain | 10 | 0.90 | 0.70 |
| vague / underspecified | 5 | 0.80 | 0.40 |
| image-grounded | 6 | 0.83 | 0.50 |
| adversarial |
Realistic OOD schema-valid: 0.61 free / 0.97 under guided_json. Strongest input variant
(prompt + brief + render): 0.73 schema-valid / 0.93 echo, free decoding. Sampling robustness at
temperature=0.7 (30 generations, 3 seeds): parse 0.97, schema-valid 0.57. Parse failures are
almost all truncation at the 13k-token cap (10/126 free generations; 0 thinking-leaks,
0 markdown fences, 1 trailing-data).
Inference: do_sample=False, repetition_penalty≈1.1, max_new_tokens≥13000; serve with
vLLM guided_json for production, re-validate with validate.py, regenerate on gate failures.
| 7 |
| 0.43 |
| 0.29 |
| off-task | 4 | 1.00 | 0.75 |