Qwen 3.8 Fable 5 Distill
Light tune on Qwen3.8 on some the datasets cited here, as well as a large corpus of personal (private) Fable 5 data
| Model | ARC Challenge | ARC Challenge (Easy) | BoolQ |
|---|---|---|---|
| Qwen3.8-27B | 0.591 | 0.782 | 0.896 |
| Qwen3.8-27B-Fable-Distill | 0.637 | 0.832 | 0.911 |
As always, big thank you to @nightmedia for the benchmarks
Notes
- The model accepts enable_thinking and a reasoning_effort of low, medium or xhigh (the template's own default is xhigh, which thinks at length every turn).
- Base model sampling recommendations: temperature 1.0, top_p 0.95, top_k 20.
The data for this model was easily formatted, validated, and masked using Teich
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.