Article
Open-source DeepResearch โ Freeing our search agents
โข
617
Brigitte Tousignant
BrigitteTousi
AI & ML interests
None yet
Recent Activity
upvoted
an
article
2 days ago
Open-source DeepResearch โ Freeing our search agents
upvoted
an
article
4 days ago
Open-R1: Update #1
Organizations
BrigitteTousi's activity
upvoted
an
article
2 days ago
upvoted
an
article
4 days ago
Article
Open-R1: Update #1
By
and 7 others
โข
โข
235
reacted to
fdaudens's
post with ๐
7 days ago
reacted to
davidberenstein1957's
post with ๐
7 days ago
Post
1532
tldr; Parquet is awesome, DuckDB too!
Datasets on the Hugging Face Hub rely on parquet files. We can interact with these files using DuckDB as a fast in-memory database system. One of DuckDBโs features is vector similarity search which can be used with or without an index.
blog:
https://huggingface.co/learn/cookbook/vector_search_with_hub_as_backend
Datasets on the Hugging Face Hub rely on parquet files. We can interact with these files using DuckDB as a fast in-memory database system. One of DuckDBโs features is vector similarity search which can be used with or without an index.
blog:
https://huggingface.co/learn/cookbook/vector_search_with_hub_as_backend
reacted to
fdaudens's
post with ๐ฅ
7 days ago
Post
3200
๐ฏ Kokoro TTS just hit v1.0! ๐
Small but mighty: 82M parameters, runs locally, speaks multiple languages. The best part? It's Apache 2.0 licensed!
This could unlock so many possibilities โจ
Check it out: hexgrad/Kokoro-82M
Small but mighty: 82M parameters, runs locally, speaks multiple languages. The best part? It's Apache 2.0 licensed!
This could unlock so many possibilities โจ
Check it out: hexgrad/Kokoro-82M
- 1 reply
reacted to
pagezyhf's
post with ๐ฅ
7 days ago
Post
1603
We published https://huggingface.co/blog/deepseek-r1-aws!
If you are using AWS, give a read. It is a running document to showcase how to deploy and fine-tune DeepSeek R1 models with Hugging Face on AWS.
We're working hard to enable all the scenarios, whether you want to deploy to Inference Endpoints, Sagemaker or EC2; with GPUs or with Trainium & Inferentia.
We have full support for the distilled models, DeepSeek-R1 support is coming soon!! I'll keep you posted.
Cheers
If you are using AWS, give a read. It is a running document to showcase how to deploy and fine-tune DeepSeek R1 models with Hugging Face on AWS.
We're working hard to enable all the scenarios, whether you want to deploy to Inference Endpoints, Sagemaker or EC2; with GPUs or with Trainium & Inferentia.
We have full support for the distilled models, DeepSeek-R1 support is coming soon!! I'll keep you posted.
Cheers
- 1 reply
liked
a
dataset
8 days ago
reacted to
AdinaY's
post with ๐ฅ
8 days ago
Post
3098
Itโs not just a flood of model releases, papers are dropping just as fast ๐
Here are the 10 most upvoted papers from the Chinese community:
๐ zh-ai-community/2025-january-papers-679933cbf0f3ced11f5a168a
Here are the 10 most upvoted papers from the Chinese community:
๐ zh-ai-community/2025-january-papers-679933cbf0f3ced11f5a168a
reacted to
davanstrien's
post with ๐
8 days ago
Post
1679
Why choose between strong LLM reasoning and efficient models?
Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT answerdotai/ModernBERT-base for fast, efficient classification.
Blog post: https://danielvanstrien.xyz/posts/2025/deepseek/distil-deepseek-modernbert.html
Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT answerdotai/ModernBERT-base for fast, efficient classification.
Blog post: https://danielvanstrien.xyz/posts/2025/deepseek/distil-deepseek-modernbert.html
liked
2
Spaces
8 days ago
reacted to
m-ric's
post with โ๐คโค๏ธ๐๐ฅ
9 days ago
Post
3543
๐ง๐ต๐ฒ ๐๐๐ฏ ๐๐ฒ๐น๐ฐ๐ผ๐บ๐ฒ๐ ๐ฒ๐
๐๐ฒ๐ฟ๐ป๐ฎ๐น ๐ถ๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ ๐ฝ๐ฟ๐ผ๐๐ถ๐ฑ๐ฒ๐ฟ๐!
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Read more in the announcement ๐ https://huggingface.co/blog/inference-providers
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Read more in the announcement ๐ https://huggingface.co/blog/inference-providers
- 1 reply
reacted to
odellus's
post with ๐ง
9 days ago
Post
1506
Tired: shitposting on bsky
Wired: shitposting on hf
Wired: shitposting on hf
- 1 reply
reacted to
chansung's
post with ๐
9 days ago
Post
1967
Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI!
It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.
Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
โฆ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
โฆ Stage 3: Fine-tuning with a careful balance of multimodal data.
Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.
The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.
It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.
Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
โฆ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
โฆ Stage 3: Fine-tuning with a careful balance of multimodal data.
Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.
The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.
reacted to
fdaudens's
post with ๐๐
9 days ago
Post
1664
๐ The open source community is unstoppable: 4M total downloads for DeepSeek models on Hugging Face, with 3.2M coming from the +600 models created by the community.
That's 30% more than yesterday!
That's 30% more than yesterday!
- 1 reply