Ella Charlaix

echarlaix

125 35 55

AI & ML interests

None yet

Recent Activity

upvoted an article 2 days ago

Hugging Face on AMD Instinct MI455X: First Transformers Results

updated a model 4 days ago

echarlaix/distilbert-base-uncased-finetuned-sst-2-english-openvino

new activity 5 days ago

optimum/documentation-images:export-space-img

View all activity

Organizations

upvoted an article 2 days ago

Article

Hugging Face on AMD Instinct MI455X: First Transformers Results

badaoui

•

3 days ago

• 13

updated a model 4 days ago

echarlaix/distilbert-base-uncased-finetuned-sst-2-english-openvino

Text Classification • Updated 4 days ago • 31.2k

New activity in optimum/documentation-images 5 days ago

export-space-img

#6 opened 5 days ago by

echarlaix

export-space

#5 opened 5 days ago by

echarlaix

liked a Space 9 days ago

Carbon

🧬

176

Explore DNA model predictions and protein folding interactively

upvoted a collection 9 days ago

🧬 Carbon

Collection

Carbon 500M, 3B, 8B genomic models and GGUF variants for llama.cpp • 7 items • Updated Jun 2 • 44

liked a Space 19 days ago

HF Realtime Voice

🎙

475

Voice chat over WebSocket against a HF speech-to-speech

upvoted an article 20 days ago

Article

LeRobot v0.6.0: Imagine, Evaluate, Improve

imstevenpmwork, pepijn223, CarolinePascal, lilkm, maximellerbach, nepyope, nikodembartnik, Nico-robot, thomwolf

•

20 days ago

• 77

commented on Optimum Intel 2.0: An OpenVINO-First Toolkit for Running Open Models on Intel about 1 month ago

If I upgrade transformers to the latest version, then optimum-cli doesn't work, as it requires transformers <5.1

@hachuah what is the exact issue you're facing ? you should be able to export gemma4 models by upgrading your transformers to v5.5 after installing optimum-intel (even though optimum-intel doesn't officially support v5.5).

Also here you're trying to export a gemma 4 unfied model, support for this architecture was introduced in https://github.com/huggingface/optimum-intel/pull/1770 and is not included in optimum-intel v2.0 (unlike gemma 4), so you'll have to install optimum-intel from source as well as transformers v5.10 (next optimum-intel release is planned for 29/07)