Downloads · 30 days
24
100% of all-time downloads
KaLM-Reranker-V1-Large-R2-Stage2-r96-a48
Yuki131/KaLM-Reranker-V1-Large-R2-Stage2-r96-a48
KaLM-Reranker-V1-Large-R2-Stage2-r96-a48 is a machine learning model from Yuki131. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
We release the checkpoints from the three-stage training pipeline described in the third version of our paper. Stage 1 uses supervised fine-tuning; Stage 2 produces two checkpoints through soft-label distillation; and…
All-time downloads
24
Public
Parameters
7.5B
15.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15 GB · 100%
At a glance
- Model type
- t5gemma2
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 23, 2026
- SHA
- 101f14a6
Model card
From the Hugging Face model README
R2 Training Checkpoints (Stages 1–3)
We release the checkpoints from the three-stage training pipeline described in the third version of our paper. Stage 1 uses supervised fine-tuning; Stage 2 produces two checkpoints through soft-label distillation; and Stage 3 combines them through model soup to produce the final R2 models.
| Stage | Checkpoint | Nano | Small | Large |
|---|---|---|---|---|
| Stage 1 | Supervised fine-tuning | KaLM-Reranker-V1-Nano-R2-Stage1 | KaLM-Reranker-V1-Small-R2-Stage1 | KaLM-Reranker-V1-Large-R2-Stage1 |
| Stage 2 | Distillation (r64-a32) | KaLM-Reranker-V1-Nano-R2-Stage2-r64-a32 | KaLM-Reranker-V1-Small-R2-Stage2-r64-a32 | KaLM-Reranker-V1-Large-R2-Stage2-r64-a32 |
| Stage 2 | Distillation (r96-a48) | KaLM-Reranker-V1-Nano-R2-Stage2-r96-a48 | KaLM-Reranker-V1-Small-R2-Stage2-r96-a48 | KaLM-Reranker-V1-Large-R2-Stage2-r96-a48 |
| Stage 3 | Final R2 model | KaLM-Reranker-V1-Nano-R2 | KaLM-Reranker-V1-Small-R2 | KaLM-Reranker-V1-Large-R2 |
- Type
- t5gemma2
- Created
- Sep 3, 2026
- Updated
- Sep 23, 2026