Mastering Tensor Dimensions in Transformers
ā¢
25
Hafedh Hichri
not-lain
AI & ML interests
custom AI models with HF integration, HuggingFace fellow š¤
Recent Activity
liked
a model
1 day ago
llamaindex/vdr-2b-multi-v1
upvoted
a
collection
1 day ago
Visual Document Retrieval
Articles
Organizations
not-lain's activity
reacted to
meg's
post with š„
about 22 hours ago
Post
2053
š«...And we're live!š« Seasonal newsletter from ethicsy folks at Hugging Face, exploring the ethics of "AI Agents"
https://huggingface.co/blog/ethics-soc-7
Our analyses found:
- There's a spectrum of "agent"-ness
- *Safety* is a key issue, leading to many other value-based concerns
Read for details & what to do next!
With @evijit , @giadap , and @sasha
https://huggingface.co/blog/ethics-soc-7
Our analyses found:
- There's a spectrum of "agent"-ness
- *Safety* is a key issue, leading to many other value-based concerns
Read for details & what to do next!
With @evijit , @giadap , and @sasha
reacted to
merve's
post with š„ā¤ļø
1 day ago
Post
3077
there's a new multimodal retrieval model in town š¤
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM šØ
> shrinkable with matryoshka šŖ
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual š
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM šØ
> shrinkable with matryoshka šŖ
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual š
posted
an
update
3 days ago
Post
3500
Published a new blogpost š
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
š https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
š https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
reacted to
hexgrad's
post with š„
5 days ago
Post
11692
š£ Looking for labeled, high-quality synthetic audio/TTS data š£ Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.
If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.
What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ā¤ļø
More details at hexgrad/Kokoro-82M#21
If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.
What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. ā¤ļø
More details at hexgrad/Kokoro-82M#21
- 18 replies
reacted to
Wauplin's
post with š¤
9 days ago
Post
2918
What a great milestone to celebrate! The huggingface_hub library is slowly becoming a cornerstone of the Python ML ecosystem when it comes to interacting with the
@huggingface
Hub. It wouldn't be there without the hundreds of community contributions and feedback! No matter if you are loading a model, sharing a dataset, running remote inference or starting jobs on our infra, you are for sure using it! And this is only the beginning so give a star if you wanna follow the project š https://github.com/huggingface/huggingface_hub
- 1 reply
reacted to
nroggendorff's
post with ā
13 days ago
Post
6257
hey nvidia, can you send me a gpu?
comment or react if you want ~~me~~ to get one too. šš
comment or react if you want ~~me~~ to get one too. šš
- 25 replies
replied to
nroggendorff's
post
13 days ago
we multiply
reacted to
ivanfioravanti's
post with š
17 days ago
Post
1549
Probably most of you already knows this trick but just in case:
š¤ Unable to connect to Hugging Face Spaces Dev Mode through local Cursor? š” Don't worry there is an easy trick!
- right click Connect with VS Code
- copy link in your browser
- vscode://vscode-remote/...
- replace vscode with cursor and go
- cursor://vscode-remote/...
š¤ Unable to connect to Hugging Face Spaces Dev Mode through local Cursor? š” Don't worry there is an easy trick!
- right click Connect with VS Code
- copy link in your browser
- vscode://vscode-remote/...
- replace vscode with cursor and go
- cursor://vscode-remote/...
reacted to
sayakpaul's
post with š„
21 days ago
Post
4015
Commits speak louder than words š¤Ŗ
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release š¤
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release š¤
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
reacted to
FranckAbgrall's
post with š„
27 days ago
Post
1128
š It should now be easier to identify discussions or pull requests where repository owners are participating on HF, let us know it that helps š¬š¤
- 1 reply
reacted to
FranckAbgrall's
post with š„š
about 1 month ago
Post
2000
Hey!
āØ If you're using HF access tokens, we just released an overview of the permissions for fine-grained tokens by hovering over the badge on token settings page (org and user)
It will show the highest permission you've set for each entity š
āØ If you're using HF access tokens, we just released an overview of the permissions for fine-grained tokens by hovering over the badge on token settings page (org and user)
It will show the highest permission you've set for each entity š
reacted to
julien-c's
post with š„
about 1 month ago
Post
8320
After some heated discussion š„, we clarify our intent re. storage limits on the Hub
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community š„
cc: @reach-vb @pierric @victor and the HF team
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community š„
cc: @reach-vb @pierric @victor and the HF team
- 28 replies
reacted to
thomwolf's
post with š„
about 1 month ago
Post
1434
Most liked and most downloaded open-source AI models from 2022 to 2024
Interactive viz: https://aiworld.eu/embed/model/model/treemap
Discussion: huggingface/open-source-ai-year-in-review-2024
Interactive viz: https://aiworld.eu/embed/model/model/treemap
Discussion: huggingface/open-source-ai-year-in-review-2024
reacted to
hexgrad's
post with š„
about 1 month ago
Post
2969
self.brag(): Kokoro finally got 300 votes in
Pendrokar/TTS-Spaces-Arena after
@Pendrokar
was kind enough to add it 3 weeks ago.Discounting the small sample size of votes, I think it is safe to say that hexgrad/Kokoro-TTS is currently a top 3 model among the contenders in that Arena. This is notable because:
- At 82M params, Kokoro is one of the smaller models in the Arena
- MeloTTS has 52M params
- F5 TTS has 330M params
- XTTSv2 has 467M params
-
- 5 replies
reacted to
loubnabnl's
post with š„
about 2 months ago
Post
1863
Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit š ļø https://github.com/huggingface/smollm/
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
reacted to
victor's
post with š„
about 2 months ago
Post
2445
Perfect example of why
Qwen/Qwen2.5-Coder-32B-Instruct is insane?
Introducing: AI Video Composer š„
huggingface-projects/ai-video-composer
Drag and drop your assets (images/videos/audios) to create any video you want using natural language!
It works by asking the model to output a valid FFMPEG and this can be quite complex but most of the time Qwen2.5-Coder-32B gets it right (that thing is a beast). It's an update of an old project made with GPT4 and it was almost impossible to make it work with open models back then (~1.5 years ago), but not anymore, let's go open weights š.
Introducing: AI Video Composer š„
huggingface-projects/ai-video-composer
Drag and drop your assets (images/videos/audios) to create any video you want using natural language!
It works by asking the model to output a valid FFMPEG and this can be quite complex but most of the time Qwen2.5-Coder-32B gets it right (that thing is a beast). It's an update of an old project made with GPT4 and it was almost impossible to make it work with open models back then (~1.5 years ago), but not anymore, let's go open weights š.
reacted to
luigi12345's
post with š
about 2 months ago
Post
3723
MinimalScrap
Only Free Dependencies. Save it.It is quite useful uh.
Only Free Dependencies. Save it.It is quite useful uh.
!pip install googlesearch-python requests
from googlesearch import search
import requests
query = "Glaucoma"
for url in search(f"{query} site:nih.gov filetype:pdf", 20):
if url.endswith(".pdf"):
with open(url.split("/")[-1], "wb") as f: f.write(requests.get(url).content)
print("ā
" + url.split("/")[-1])
print("Done!")
reacted to
merve's
post with ā¤ļø
about 2 months ago
Post
3163
your hugging face profile now has your recent activities š¤