GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SadilKhan
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
SadilKhan
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3-4B |
| Adapter type | LoRA |
| Fine-tuning framework | ms-swift |
| Checkpoint step | 180,000 |
bash
pip install ms-swift transformers peft torchpython
from swift.llm import PtEngine, RequestConfig, InferRequest engine = PtEngine( "Qwen/Qwen3-4B", adapters=["SadilKhan/NURBGen"], use_hf=True, torch_dtype="bfloat16", device_map="auto", attn_impl="flash_attn_2", use_cache=True,) response = engine.infer( [InferRequest(messages=[{ "role": "user", "content": "Generate NURBS for the following: Design a rectangular plate with dimensions 330.20 mm x 233.40 mm x 6.00 mm. Include two square through-holes near each end." }])], request_config=RequestConfig( max_tokens=8192, temperature=0.3, ),) print(response[0].choices[0].message.content)You need to install vllm to use the VllmEngine, which is much faster and more memory efficient than the PtEngine for long generations. See ms-swift docs for installation instructions. pip install vllm==0.11.0
python
import torchfrom swift.infer_engine import VllmEnginefrom swift.llm import InferRequest, RequestConfig engine = VllmEngine( "Qwen/Qwen3-4B", adapters=["SadilKhan/NURBGen"], # one LoRA adapter use_hf=True, torch_dtype=torch.bfloat16, max_model_len=8192, # set only as large as you need gpu_memory_utilization=0.9, max_num_seqs=8, # useful if you batch multiple requests max_lora_rank=64, # increase if your LoRA rank is >16) requests = [ InferRequest( messages=[{ "role": "user", "content": ( "Generate NURBS for the following: " "Design a rectangular plate with dimensions " "330.20 mm x 233.40 mm x 6.00 mm. " "Include two square through-holes near each end." ) }] )] config = RequestConfig( max_tokens=8192, # much faster than 8192 unless you truly need that length temperature=0.3, # greedy decode = faster) responses = engine.infer(requests, config)print(responses[0].choices[0].message.content)python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel base_model_id = "Qwen/Qwen3-4B"adapter_id = "SadilKhan/NURBGen" tokenizer = AutoTokenizer.from_pretrained(base_model_id)model = AutoModelForCausalLM.from_pretrained( base_model_id, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter_id)model.eval() prompt = "Generate NURBS for the following: Design a small table with rounded edges and tapered legs. Include four dowel pins along one side for assembly. The table has chamfers at specific corners and fillets on its underside for smooth transitions. Dimensions: length 23.75 mm, width 70.00 mm, height 27.50 mm."messages = [{"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=8192, temperature=0.3, do_sample=False, ) result = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(result)If you use NURBGen in your research, please cite:
bibtex
@inproceedings{usama2026nurbgen, title={NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling}, author={Usama, Muhammad and Khan, Mohammad Sadil and Stricker, Didier and Afzal, Muhammad Zeshan}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={40}, number={12}, pages={9603--9611}, year={2026}}from swift.llm import PtEngine, RequestConfig, InferRequest engine = PtEngine( "Qwen/Qwen3-4B", adapters=["SadilKhan/NURBGen"], use_hf=True, torch_dtype="bfloat16", device_map="auto", attn_impl="flash_attn_2", use_cache=True,) response = engine.infer( [InferRequest(messages=[{ "role": "user", "content": "Generate NURBS for the following: Design a rectangular plate with dimensions 330.20 mm x 233.40 mm x 6.00 mm. Include two square through-holes near each end." }])], request_config=RequestConfig( max_tokens=8192, temperature=0.3, ),) print(response[0].choices[0].message.content)import torchfrom swift.infer_engine import VllmEnginefrom swift.llm import InferRequest, RequestConfig engine = VllmEngine( "Qwen/Qwen3-4B", adapters=["SadilKhan/NURBGen"], # one LoRA adapter use_hf=True, torch_dtype=torch.bfloat16, max_model_len=8192, # set only as large as you need gpu_memory_utilization=0.9, max_num_seqs=8, # useful if you batch multiple requests max_lora_rank=64, # increase if your LoRA rank is >16) requests = [ InferRequest( messages=[{ "role": "user", "content": ( "Generate NURBS for the following: " "Design a rectangular plate with dimensions " "330.20 mm x 233.40 mm x 6.00 mm. " "Include two square through-holes near each end." ) }] )] config = RequestConfig( max_tokens=8192, # much faster than 8192 unless you truly need that length temperature=0.3, # greedy decode = faster) responses = engine.infer(requests, config)print(responses[0].choices[0].message.content)import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel base_model_id = "Qwen/Qwen3-4B"adapter_id = "SadilKhan/NURBGen" tokenizer = AutoTokenizer.from_pretrained(base_model_id)model = AutoModelForCausalLM.from_pretrained( base_model_id, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter_id)model.eval() prompt = "Generate NURBS for the following: Design a small table with rounded edges and tapered legs. Include four dowel pins along one side for assembly. The table has chamfers at specific corners and fillets on its underside for smooth transitions. Dimensions: length 23.75 mm, width 70.00 mm, height 27.50 mm."messages = [{"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=8192, temperature=0.3, do_sample=False, ) result = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(result)@inproceedings{usama2026nurbgen, title={NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling}, author={Usama, Muhammad and Khan, Mohammad Sadil and Stricker, Didier and Afzal, Muhammad Zeshan}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={40}, number={12}, pages={9603--9611}, year={2026}}