BBC-Esq
Your usage of ModelFilter and possibly "DatasetFilter" from the ```huggingface_hub``` library is out of date. Apparently those were removed in this here: https://github.com/huggingface/huggingface_hub/commit/bb38f9422cb88ba02694c87fb5979cc48ecef8a0#diff-1b045ed2e860a78218b3501b6b8df1f5609c493c1e2fa16769486fb020f7c164 I noticed this when trying to implement...
Has anyone had luck converting the model located here: https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407 I haven't. I've even tried renaming the ```consolidated.safetensors``` file to ```model.safetensors``` just to be safe, but no dice. I'm wondering...
Hello, It might be possible to convert multiple model architectures to Llama in order make them compatible with ```Ctranslate2``` much faster than having to create a converter for every new...
Why does release 28 say it removes conda wheels for python 3.11 but then it states it added them?
Very user friendly converter to the ```ctranslate2``` format. It can convert to multiple quants in one go.
I noticed that the latest benchmark from whisper.cpp is from February 2, 2023 and presumably the others are equally outdated. Can someone please do updated benchmarks for the three backends...
https://github.com/openai/whisper/discussions/2363
https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5
https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat