PKU-DS-LAB
/

FairyR1-32B

@@ -20,7 +20,6 @@ library_name: transformers
 FairyR1-32B, a highly efficient large-language-model (LLM) that matches or exceeds larger models on select tasks despite using only ~5% of their parameters. Built atop the DeepSeek-R1-Distill-Qwen-32B base, FairyR1-32B leverages a novel “distill-and-merge” pipeline—combining task-focused fine-tuning with model-merging techniques to deliver competitive performance with drastically reduced size and inference cost. This project was funded by NSFC, Grant 624B2005.
 ## Model Details
 The FairyR1 model represents a further exploration of our earlier work [TinyR1](https://arxiv.org/pdf/2503.04872), retaining the core “Branch-Merge Distillation” approach while introducing refinements in data processing and model architecture.
@@ -37,7 +36,6 @@ These results indicate that, by building on the DeepSeek‑R1‑Distill‑Qwen
 This work demonstrates the feasibility of significantly reducing model size and potential inference cost through optimized data processing and model fusion techniques while maintaining strong task-specific performance.
 ## Model Description
 - **Developed by:** PKU-DS-LAB
@@ -64,7 +62,6 @@ This work demonstrates the feasibility of significantly reducing model size and
 - [LiveCodeBench (code)](https://huggingface.co/datasets/livecodebench/code_generation_lite):  We evaluate 8 times and report the average accuracy. The dataset version is "release_v5" (date range: 2024-08-01 to 2025-02-01), consisting of 279 problems.<br>
 - [GPQA-Diamond (Sci-QA)](https://huggingface.co/datasets/Idavidrein/gpqa):  We evaluate 8 times and report the average accuracy. The dataset consists of 198 problems.<br>
 ## FairyR1 series Team Members:
 Leading By:

 FairyR1-32B, a highly efficient large-language-model (LLM) that matches or exceeds larger models on select tasks despite using only ~5% of their parameters. Built atop the DeepSeek-R1-Distill-Qwen-32B base, FairyR1-32B leverages a novel “distill-and-merge” pipeline—combining task-focused fine-tuning with model-merging techniques to deliver competitive performance with drastically reduced size and inference cost. This project was funded by NSFC, Grant 624B2005.
 ## Model Details
 The FairyR1 model represents a further exploration of our earlier work [TinyR1](https://arxiv.org/pdf/2503.04872), retaining the core “Branch-Merge Distillation” approach while introducing refinements in data processing and model architecture.
 This work demonstrates the feasibility of significantly reducing model size and potential inference cost through optimized data processing and model fusion techniques while maintaining strong task-specific performance.
 ## Model Description
 - **Developed by:** PKU-DS-LAB
 - [LiveCodeBench (code)](https://huggingface.co/datasets/livecodebench/code_generation_lite):  We evaluate 8 times and report the average accuracy. The dataset version is "release_v5" (date range: 2024-08-01 to 2025-02-01), consisting of 279 problems.<br>
 - [GPQA-Diamond (Sci-QA)](https://huggingface.co/datasets/Idavidrein/gpqa):  We evaluate 8 times and report the average accuracy. The dataset consists of 198 problems.<br>
 ## FairyR1 series Team Members:
 Leading By: