Downloads · 30 days
5
23% of all-time downloads
Affine-5csd7rdje4-r1b
saysth/Affine-5csd7rdje4-r1b
Affine-5csd7rdje4-r1b is a image-text-to-text model from saysth. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.
All-time downloads
22
Public
Parameters
34.7B
70.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors70.2 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- qwen3_5_moe
- Access
- Public
- Created
- Aug 11, 2026
- Updated
- Aug 11, 2026
- SHA
- 59f3f32f
Try a prompt
Base models
Model card
From the Hugging Face model README
saysth/Affine-5csd7rdje4-r1b
Affine SN120 Reason v3 R1b challenger.
- Base king:
Tok331102/affine-5EqYW8McUc-af10@eb8bf9a356a254f71faaa439e8abc3cfba572c53 - Train: LoRA SFT r=16 α=32, max_len=16384, 1 epoch, lr=1e-5, 47 steps, 1507 high-Reason rows
- Visual tower grafted via compact
king-extra-visual.safetensors - Submit hotkey: h02 (
5CSd73v8fQTHK9B1cLvebvM9q4qYNgdbAZu6V8bpjRJRDje4) - Local n80 screen incomplete on H200 (teacher decode bottleneck); re-duel before crown submit
Adapter (private): saysth/Affine-5csd7rdje4-r1b-adapter
Meta: saysth/affine-r1b-export
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5_moe
- Created
- Aug 11, 2026
- Updated
- Aug 11, 2026