Image-Text-to-Text
PEFT
Safetensors
English
Chinese
decision-model
judgment
classification
vision-language
jev
systemone
qwen3.5
lora
vev
Eval Results (legacy)
Instructions to use CountingSheep/vev-4b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use CountingSheep/vev-4b-lora with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Commit History
16 days ago
-
Card: calibration error over the 18 release sets
Verified signature9fb474f -
Card: the second generation of the 4B model is CountingSheep/vev-4b-v2
Verified signaturef7ad89f -
Card: vev-4b 0.2.0 is out; this repository stays at 0.1.0
Verified signature80e933d
-
Card: link the browser demo Space
Verified signature8b9a9c5
-
Card: add the real-time Doom clip at the top
Verified signaturedbc2b23
-
Card: drop the POPE sentence
Verified signature52c72f8 -
Card: replace the trust section with Limitations
Verified signaturefce15c6 -
Card: add qwen3.5 / lora tags
Verified signature6f7d3c0 -
Card: new positioning, image example, trust section
Verified signaturefdd7271
-
Model card: adapter loading that also works offline; link the prompt description
Verified signature247c2ae -
Add the Qwen Apache-2.0 license, fix the loading examples, link the release; drop local_files_only
Verified signatureec2ad4e -
Model card: install from GitHub, adapter wording, wrapped paragraphs
Verified signature4c16949 -
Checkpoint marker is vev.json; drop the unused head.pt
Verified signature033cc06 -
Card: Jev training statement
Verified signature40e8bd2 -
Card: Jev used for evaluation only
Verified signaturee9f6767 -
Add model card
Verified signaturec66fe4e -
Upload vev-4b-lora v0.1.0 weights
Verified signature90b3446 -
initial commit
Verified signaturece316ff