Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Convrot conversion of qwen3vl 4b. near identical to bf16 in terms of adherence and quality and usually near identical output to bf16. the learned version might slightly outperform the simple. but simple handles the...
Source du modèle
Description de la source
Convrot conversion of qwen3vl 4b. near identical to bf16 in terms of adherence and quality and usually near identical output to bf16. the learned version might slightly outperform the simple. but simple handles the bf16 layers differently and you might prefer that one.
optimized fork of Ai-Toolkit
https://github.com/PlagueKind/BlackTrainer
If you want to support my work I accept XMR monero
865BrcfWLdwELwuq5faV1uVTbh93zVK6AUYLY2c3mX6sFfAGRfS6axe1kBTYYKuM7ccN7zBZDAZvnT7E4NKmUazySdbpc7p
Sources
1 sourceVérifié 18 oct.
Artefacts du modèle
1 artefactqwen3vl_4b_int8_convrot_learned.safetensors
safetensors · INT8 · 4,89 GB · SHA-256 6fe6c6aa2f1b…f534 · Hugging Face
TéléchargerExtraits de sources
2 extraits--- base_model: Qwen/Qwen3-VL-4B-Instruct tags: - qwenvl - qwen - text - encoder - krea - krea2 --- Convrot conversion of qwen3vl 4b. near identical to bf16 in terms of adherence and quality and usually near identical output to bf16. the learned version might slightly outperform the simple. but simple handles the bf16 layers differently and you might prefer that one. optimized fork of Ai-Toolkit https://github.com/PlagueKind/BlackTrainer If you want to support my work I accept XMR monero ```865BrcfWLdwELwuq5faV1uVTbh93zVK6AUYLY2c3mX6sFfAGRfS6axe1kBTYYKuM7ccN7zBZDAZvnT7E4NKmUazySdbpc7p```
Source context: 0 downloads · 4 likes · Repo Plaguekind/qwen3vl-4b-int8-convrot
