Thanks for the notification! Indeed we support only Linux for now. We would be happy to work on the token problem. If you could share your colab config and the trace here or on our discord, it would help us :)
Bertrand Charpentier
sharpenb
AI & ML interests
Efficient & Reliable ML
Recent Activity
replied to
their
post
3 days ago
We compressed SmolLMs to make 135 variations of them (see https://huggingface.co/PrunaAI?search_models=smolLM) with different quantization configurations with `pruna` (https://docs.pruna.ai/en/latest/).
We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
Organizations
sharpenb's activity
replied to
their
post
3 days ago
Wrong automatic detection of nb of parameters & precision (dataset card bug)
1
#5 opened 4 days ago
by
Jeronymous
Wrong automatic detection of nb of parameters & precision (dataset card bug)
1
#4 opened 4 days ago
by
Jeronymous
Can't get attribute'EmbedND'
2
#3 opened 3 months ago
by
oguzhanercan
config.json
2
#2 opened 2 months ago
by
sdyy
how to use comfyui?
1
#3 opened about 1 month ago
by
srsuzume
SOMEONE ALREADY USED PRUNA ON IT
2
#2 opened about 1 month ago
by
Austinkeith2010
Thankyou !
1
#2 opened about 1 month ago
by
prithivMLmods
Why don't you include the tokenizer ?
3
#2 opened 5 days ago
by
Jeronymous
posted
an
update
5 days ago
Post
1826
We compressed SmolLMs to make 135 variations of them (see https://huggingface.co/PrunaAI?search_models=smolLM) with different quantization configurations with
We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
pruna (https://docs.pruna.ai/en/latest/). We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
-
- 3 replies
updated
a
Space
13 days ago
Upload folder using huggingface_hub
2
#1 opened 16 days ago
by
sharpenb
updated
a
model
16 days ago
Upload folder using huggingface_hub
2
#1 opened 16 days ago
by
sharpenb
updated
a
model
16 days ago
New activity in
PrunaAI/jasonkrone-pythia-1-dot-4b-deduped-111b-toks-mc-finetune-hpo-lr-with-mmlu-bnb-8bit-smashed
16 days ago
Upload folder using huggingface_hub
2
#1 opened 16 days ago
by
sharpenb
Upload folder using huggingface_hub
2
#1 opened 16 days ago
by
sharpenb
updated
a
model
16 days ago
Upload folder using huggingface_hub
2
#1 opened 16 days ago
by
sharpenb
updated
a
model
16 days ago