This commit is contained in:
Xin Cheng
2026-06-28 20:53:08 +08:00
parent f9879b5c1f
commit dd854392fa
+2 -1
View File
@@ -52,7 +52,8 @@ bash scripts/eval/eval.sh
### Released Checkpoints
The checkpoints below are the ones used for Table 1 in the paper. They were trained on the `perfect-blend` data generated in non-thinking mode.
The checkpoints below are the ones used for Table 1 in the [paper](./DSpark_paper.pdf). Each checkpoint was trained on [open-perfectblend](https://huggingface.co/datasets/mlabonne/open-perfectblend) data generated by its corresponding target model in non-thinking mode, and is the direct output of the corresponding training configuration under [config/](./config/).
| Algorithm | `Qwen/Qwen3-4B` | `Qwen/Qwen3-8B` | `Qwen/Qwen3-14B` | `google/gemma-4-12B-it` |
| --- | --- | --- | --- | --- |