3DOnt NL-2-SPARQL parser โ€” medium (4B), Hugging Face (transformers)

Qwen/Qwen3.5-4B fine-tuned with LoRA (rank 16, 1 epoch) on the NL-2-SPARQL dataset of 3DOnt (original questions + generated new logical structures + about 10,000 hand-written questions + 1,385 hand-written questions with implicit relationships): it parses a natural-language question about a 3D point cloud and its ontology into the five lists L1..L5 that the NL-2-SPARQL library of the 3DGraphExplorer turns into SPARQL.

System prompt (as in training): You will receive a natural language query by the user. you just have to parse it. do not say anything else. Chat template of the base model with thinking disabled (enable_thinking=False).

Repositories: 3DOMFBK/3dont-nl2sparql-medium (Hugging Face format), 3DOMFBK/3dont-nl2sparql-medium-mlx (MLX 4-bit, 3DGraphExplorer on Apple Silicon), 3DOMFBK/3dont-nl2sparql-medium-MLC (WebGPU q4f16_1, online demo).

Downloads last month
26
Safetensors
Model size
5B params
Tensor type
BF16
ยท
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for 3DOMFBK/3dont-nl2sparql-medium

Finetuned
Qwen/Qwen3.5-4B
Adapter
(1,207)
this model