GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
caid-technologies
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
caid-technologies
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Give it a hardware idea and it returns, as one machine-readable JSON object, any of:
Ask for the complete plan, or just one piece (like only the parts list).
We test on projects it has never seen during training. How often it produces a valid, well-structured result for each task:
| Task | Valid result |
|---|---|
| 🛠️ Build steps | ~100% |
| ✅ Design check | ~100% |
| 📋 Parts list | ~95% |
| 📦 Full project plan | ~85–97% |
| 🔌 Wiring map | ~67% |
It's strongest at build steps, design checks, and parts lists; full end-to-end plans are close behind; wiring maps are the hardest. Figures are from held-out testing and are being finalized for the current version.
Because it's a small model, treat the output as a helpful first draft to review, not a finished design.
parti-vision (9B, multimodal).python
from transformers import AutoModelForCausalLM, AutoTokenizer REPO = "caid-technologies/parti-base"model = AutoModelForCausalLM.from_pretrained(REPO, device_map="auto", torch_dtype="bfloat16")tok = AutoTokenizer.from_pretrained(REPO) msgs = [ {"role": "system", "content": "You design maker/electronics products. Given a request, reply with a single JSON object " "describing the complete build plan. Output only the JSON."}, {"role": "user", "content": "A compact desk clock with an e-ink display and an IR remote."},]inputs = tok.apply_chat_template( msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**inputs, max_new_tokens=6144, do_sample=False, repetition_penalty=1.1, pad_token_id=tok.eos_token_id)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))💡 Tips: keep do_sample=False (greedy — sampling degrades the JSON), keep
max_new_tokens high (≥ 6000) so long plans aren't cut off, and keep repetition_penalty=1.1 so
wiring lists don't get stuck repeating. For Ollama / local apps, convert to GGUF with llama.cpp.
caid-technologies/parti-vision,
the 9B multimodal model.bibtex
@misc{parti_base, title = {Parti-Base}, author = {Caid Technologies}, year = {2026}, howpublished = {\url{https://huggingface.co/caid-technologies}}}from transformers import AutoModelForCausalLM, AutoTokenizer REPO = "caid-technologies/parti-base"model = AutoModelForCausalLM.from_pretrained(REPO, device_map="auto", torch_dtype="bfloat16")tok = AutoTokenizer.from_pretrained(REPO) msgs = [ {"role": "system", "content": "You design maker/electronics products. Given a request, reply with a single JSON object " "describing the complete build plan. Output only the JSON."}, {"role": "user", "content": "A compact desk clock with an e-ink display and an IR remote."},]inputs = tok.apply_chat_template( msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**inputs, max_new_tokens=6144, do_sample=False, repetition_penalty=1.1, pad_token_id=tok.eos_token_id)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))@misc{parti_base, title = {Parti-Base}, author = {Caid Technologies}, year = {2026}, howpublished = {\url{https://huggingface.co/caid-technologies}}}