Arthur Zucker's picture

Arthur Zucker

ArthurZ

·

AI & ML interests

None yet

Recent Activity

reacted to danieldk's post with 🤗 5 days ago

We have been working on a project called `kernels`. `kernels` makes it possible to load compute kernels directly from the Hub! 🚀 We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release: - New layer API with `torch.compile` support. - Experimental support for loading Apple Silicon Metal 🤘 Kernels. - Generate wheels from Hub kernels for legacy deployments. Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0

reacted to danieldk's post with 🔥 5 days ago

We have been working on a project called `kernels`. `kernels` makes it possible to load compute kernels directly from the Hub! 🚀 We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release: - New layer API with `torch.compile` support. - Experimental support for loading Apple Silicon Metal 🤘 Kernels. - Generate wheels from Hub kernels for legacy deployments. Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0

liked a Space 12 days ago

nanotron/ultrascale-playbook

View all activity

Organizations

New activity in mistralai/Devstral-Small-2505 about 1 month ago

Adding transformers tag for better tracking of library

#2 opened about 1 month ago by

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct about 2 months ago

No attribute `sliding_window`?

#59 opened 3 months ago by

Does LLama4 have chunked attention in generation phase ?

#64 opened 3 months ago by

New activity in meta-llama/Llama-4-Maverick-17B-128E-Instruct 3 months ago

remove <|finetune_right_pad_id|> and change pad_token to <|finetune_right_pad|>

#25 opened 3 months ago by

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct 3 months ago

pad error

#25 opened 3 months ago by

Bug in AutoModel

#26 opened 3 months ago by

New activity in meta-llama/Llama-4-Scout-17B-16E 3 months ago

Cannot generate with BS > 1

#25 opened 3 months ago by

New activity in meta-llama/Llama-4-Maverick-17B-128E-Instruct 3 months ago

change to spda

#14 opened 3 months ago by

New activity in mistral-community/pixtral-12b 5 months ago

Fastest way for inference?

#28 opened 5 months ago by

New activity in deepseek-ai/DeepSeek-R1 5 months ago

model-00078-of-000163.safetensors not marked safe?

#80 opened 5 months ago by

New activity in mistralai/Pixtral-Large-Instruct-2411 8 months ago

Upload transformers version

#3 opened 8 months ago by

New activity in huggingface/documentation-images 8 months ago

Upload Meta-Llama-3-8B-Instruct, seqlen = 512, python, w_ compile.png

#392 opened 8 months ago by

New activity in mistral-community/pixtral-12b 9 months ago

Update model weight

#13 opened 9 months ago by

Update hidden_act to silu

#14 opened 9 months ago by

New activity in rhymes-ai/Aria 9 months ago

llama.cpp support

#1 opened 9 months ago by

New activity in google/gemma-2-2b-jpn-it 9 months ago

tokenizer_config.json is different from gemma-2-2b-it

#8 opened 9 months ago by

New activity in mistral-community/pixtral-12b 9 months ago

How can i use the full 24GB model instead of this separated safetensors files?

#8 opened 9 months ago by

New activity in meta-llama/Llama-3.2-11B-Vision-Instruct 10 months ago

hidden_activation vs hidden_act in config.json

#10 opened 10 months ago by

New activity in mistral-community/pixtral-12b-240910 10 months ago

How to use safetensors?

#13 opened 10 months ago by

New activity in mistral-community/pixtral-12b 10 months ago

lamma cpp ht to gguf not working

#2 opened 10 months ago by