Downloads · 30 days
7
23% of all-time downloads
FosCap-Qwen3.6-35B-A3B-Stage3
LockOnN/FosCap-Qwen3.6-35B-A3B-Stage3
FosCap-Qwen3.6-35B-A3B-Stage3 is a image-text-to-text model from LockOnN. 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. The card lists the license as other.
Final Stage 3 full fine-tune for the FosCap three-stage fossil-image understanding and captioning pipeline. It continues from Stage 2 and was trained on foscapstage3newvisualexpert.
All-time downloads
30
Public
Parameters
665K
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
- License
- other
- Model type
- qwen3_5_moe
- Access
- Public
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026
- SHA
- dec8117f
Try a prompt
Base models
Model card
From the Hugging Face model README
FosCap Qwen3.6-35B-A3B Stage 3
Final Stage 3 full fine-tune for the FosCap three-stage fossil-image understanding and captioning pipeline.
It continues from Stage 2 and was trained on
foscap_stage3_new_visual_expert.
Training summary
- Learning rate:
1e-5 - Epochs:
3 - Seed:
668 - Effective training batch size:
64 - Framework: LLaMA-Factory / Transformers
Only the final checkpoint is published in this repository; the redundant intermediate checkpoint-45 training
snapshot is intentionally omitted.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5_moe
- License
- other
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026