Hugging Face's logo

open/ acc

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

takarajordan  updated a Space 12 days ago
open-acc/README
takarajordan  new activity 12 days ago
open-acc/README:Update README.md
alvanlii  new activity 20 days ago
open-acc/README:[15/ 12] What are you working on this week! 💪
View all activity

open-acc's activity

cfahlgren1 
posted an update about 12 hours ago
view post
Post
343
You'll notice the AI in the SQL Console is much better at working with chatml conversations:

Here's example of unnesting the cfahlgren1/react-code-instructions in less than 10 seconds by asking it. Check it out here: cfahlgren1/react-code-instructions

- "show me the average assistant response length"
- "extract user, system, and assistant messages into separate columns"

It's super easy to work with conversational datasets now with natural language 🗣️
1aurent 
posted an update 3 days ago
merve 
posted an update 4 days ago
view post
Post
3750
supercharge your LLM apps with smolagents 🔥

however cool your LLM is, without being agentic it can only go so far

enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!

Here's our blog for you to get started https://huggingface.co/blog/smolagents
cfahlgren1 
posted an update 5 days ago
merve 
posted an update 10 days ago
takarajordan 
updated a Space 12 days ago
takarajordan 
in open-acc/README 12 days ago

Update README.md
#10 opened 12 days ago by
takarajordan
fuzzy-mittenz 
posted an update 12 days ago
view post
Post
1429
So a cool thing happened,
Nomic/GPT4ALL released a "Reasoning/Thinking"(QwQ/o1/o3 type) Model using JavaScript functions to calculate things like the haversine function for distance between two places and so on, it's VERY cool the complex calculative/recursive AI in such a small package..

I was able to adapt their methods to one of my small models "Replicant" 2gb and created a new model with importance matrix Quantization using "THE_KEY" Dataset for better inference in the coding model I pulled from Whiterabbitneo's Qwen2.5 model... I give you Reasoning Rabbit.. enjoy

IntelligentEstate/o3-ReasoningRabbit_Q2.5-Cd-7B-IQ4_XS-GGUF
-IntelligentEstate/o3-ReasoningRabbit_Q2.5-Cd-7B-IQ4_XS-GGUF

IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF
IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF

-WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
s3nh 
posted an update 16 days ago
view post
Post
1738
Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

https://huggingface.co/SmolTuners
·
merve 
posted an update 17 days ago
view post
Post
2731
Aya by Cohere For AI can now see! 👀

C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️

The authors extend Llava dataset using Aya's translation capabilities with 558k examples!
ry it here kkr5155/maya_demo

Dataset maya-multimodal/pretrain

Model maya-multimodal/maya 👏
kudos @nahidalam and team
  • 1 reply
·
merve 
posted an update 18 days ago
view post
Post
3159
Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models 🧶

✨ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2
✨ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench

The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work ⏯️

Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B
they evaluate sampling strategies, scaling laws for models and datasets, video representation and more!
> The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled 📈 scaling dataset has diminishing returns for smaller models
> They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal
> They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2
they find google/siglip-so400m-patch14-384 to be most powerful 🔥
> they also compare freezing different parts of models, training all stages with some frozen parts give the best yield

They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models 🔥
·
fuzzy-mittenz 
posted an update 19 days ago
view post
Post
594
8pm est New Discussion on AI privatization and it's importance for cooperative and confidential development, client services, and family use.

We can also touch on the NEW OPEN SOURCE which will solve MANY of the current problems we face not only with AI but as a society.
8pm
(Sorry upon startup some guy hacked the chat or simply crashed it)
new link for 8pm est
https://x.com/i/spaces/1MnxnDQrkjYGO
  • 1 reply
·
alvanlii 
in open-acc/README 20 days ago

[15/ 12] What are you working on this week! 💪
#9 opened 20 days ago by
alvanlii
merve 
posted an update 23 days ago
view post
Post
1739
A complete RAG pipeline includes a reranker, which ranks the documents to find the best document 📓
Same goes for multimodal RAG, multimodal rerankers which we can integrate to multimodal RAG pipelines!
Learn how to build a complete multimodal RAG pipeline with vidore/colqwen2-v1.0 as retriever, lightonai/MonoQwen2-VL-v0.1 as reranker, Qwen/Qwen2-VL-7B-Instruct as VLM in this notebook that runs on a GPU as small as L4 🔥 https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
bartowski 
posted an update 24 days ago
view post
Post
11769
Looks like Q4_0_N_M file types are going away

Before you panic, there's a new "preferred" method which is online (I prefer the term on-the-fly) repacking, so if you download Q4_0 and your setup can benefit from repacking the weights into interleaved rows (what Q4_0_4_4 was doing), it will do that automatically and give you similar performance (minor losses I think due to using intrinsics instead of assembly, but intrinsics are more maintainable)

You can see the reference PR here:

https://github.com/ggerganov/llama.cpp/pull/10446

So if you update your llama.cpp past that point, you won't be able to run Q4_0_4_4 (unless they add backwards compatibility back), but Q4_0 should be the same speeds (though it may currently be bugged on some platforms)

As such, I'll stop making those newer model formats soon, probably end of this week unless something changes, but you should be safe to download and Q4_0 quants and use those !

Also IQ4_NL supports repacking though not in as many shapes yet, but should get a respectable speed up on ARM chips, PR for that can be found here: https://github.com/ggerganov/llama.cpp/pull/10541

Remember, these are not meant for Apple silicon since those use the GPU and don't benefit from the repacking of weights
·
thomwolf 
posted an update 26 days ago
view post
Post
4528
We are proud to announce HuggingFaceFW/fineweb-2: A sparkling update to HuggingFaceFW/fineweb with 1000s of 🗣️languages.

We applied the same data-driven approach that led to SOTA English performance in🍷 FineWeb to thousands of languages.

🥂 FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.

The dataset is released under the permissive 📜 ODC-By 1.0 license, and the 💻 code to reproduce it and our evaluations is public.

We will very soon announce a big community project, and are working on a 📝 blogpost walking you through the entire dataset creation process. Stay tuned!

In the mean time come ask us question on our chat place: HuggingFaceFW/discussion

H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
  • 2 replies
·
merve 
posted an update 27 days ago
view post
Post
5558
This week in open-source AI was insane 🤠 A small recap🕺🏻 merve/dec-6-releases-67545caebe9fc4776faac0a3

Multimodal 🖼️
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants 👏
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license ✨
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts

LLMs 💬
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license 🔥
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! 🔥 nearly 8TB pretraining data in many languages!

Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux

Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community
merve 
posted an update 28 days ago
dvilasuero 
authored a paper 29 days ago
dvilasuero 
posted an update 29 days ago
view post
Post
2281
🌐 Announcing Global-MMLU: an improved MMLU Open dataset with evaluation coverage across 42 languages, built with Argilla and the Hugging Face community.

Global-MMLU is the result of months of work with the goal of advancing Multilingual LLM evaluation. It's been an amazing open science effort with collaborators from Cohere For AI, Mila - Quebec Artificial Intelligence Institute, EPFL, Massachusetts Institute of Technology, AI Singapore, National University of Singapore, KAIST, Instituto Superior Técnico, Carnegie Mellon University, CONICET, and University of Buenos Aires.

🏷️ +200 contributors used Argilla MMLU questions where regional, dialect, or cultural knowledge was required to answer correctly. 85% of the questions required Western-centric knowledge!

Thanks to this annotation process, the open dataset contains two subsets:

1. 🗽 Culturally Agnostic: no specific regional, cultural knowledge is required.
2. ⚖️ Culturally Sensitive: requires dialect, cultural knowledge or geographic knowledge to answer correctly.

Moreover, we provide high quality translations of 25 out of 42 languages, thanks again to the community and professional annotators leveraging Argilla on the Hub.

I hope this will ensure a better understanding of the limitations and challenges for making open AI useful for many languages.

Dataset: CohereForAI/Global-MMLU