DSR Formalizer
The DSR Formalizer was created by applying LoRA fine-tuning to Qwen2.5-7B-Instruct with the training dataset.
Model source
- Kind
- LoRA
- File size
- 4.54 GB
- Base model
- Qwen2.5
- Version
- vmodel-00001-of-00004
- Updated
- Oct 9, 2026
- Publisher
- @XiaoyangLiu-sjtu
- Source
- Hugging Face
Source description
The DSR Formalizer was created by applying LoRA fine-tuning to Qwen2.5-7B-Instruct with the training dataset.
The instruction used for fine-tuning is as follows. To ensure model performance, please use the same instruction for inference.
Please translate the natural language component into Lean4 code, and then parse it into a structured operator tree in JSON format. Use 'formal_content' for the operator logic (with ' ' as placeholders) and 'children' for the nested arguments.\nComponent: {text}\nTag: {tag}
Sources
1 source
Sources
1 sourceVerified Sep 13
Model artifacts
1 artifact
Model artifacts
1 artifactmodel-00001-of-00004.safetensors
safetensors · 4.54 GB · SHA-256 cbbc07ab52da…bb21 · Hugging Face
DownloadSource excerpts
3 excerpts
Source excerpts
3 excerptsThe DSR Formalizer was created by applying LoRA fine-tuning to Qwen2.5-7B-Instruct with the training dataset. The instruction used for fine-tuning is as follows. To ensure model performance, please use the same instruction for inference. Please translate the natural language component into Lean4 code, and then parse it into a structured operator tree in JSON format. Use 'formal_content' for the operator logic (with '<SLOT>' as placeholders) and 'children' for the nested arguments.\nComponent: {text}\nTag: {tag}
Source context: 8 downloads · 1 likes · Repo XiaoyangLiu-sjtu/DSR_Formalizer
Source context: 4 downloads · 1 likes · Repo XiaoyangLiu-sjtu/DSR_Formalizer
