Hugging Face's logo

Open-Source AI Meetup
community
Activity Feed Request to join this org

AI & ML interests

Open science and open source

Recent Activity

1024m  authored a paper 6 days ago
Query Attribute Modeling: Improving search relevance with Semantic Search and Meta Data Filtering
1024m  authored a paper 8 days ago
DSBC : Data Science task Benchmarking with Context engineering
ethanhe  authored a paper 4 months ago
Training Video Foundation Models with NVIDIA NeMo
View all activity

Nymbo 
posted an update about 2 months ago
view post
Post
2584
Anyone know how to reset Claude web's MCP config? I connected mine when the HF MCP first released with just the default example spaces added. I added lots of other MCP spaces but Claude.ai doesn't update the available tools... "Disconnecting" the HF integration does nothing, deleting it and adding it again does nothing.

Refreshing tools works fine in VS Code because I can manually restart it in mcp.json, but claude.ai has no such option. Anyone got any ideas?
·
Nymbo 
posted an update 3 months ago
view post
Post
4042
Haven't seen this posted anywhere - Llama-3.3-8B-Instruct is available on the new Llama API. Is this a new model or did someone mislabel Llama-3.1-8B?
  • 1 reply
·
Nymbo 
posted an update 4 months ago
view post
Post
2760
PSA for anyone using Nymbo/Nymbo_Theme or Nymbo/Nymbo_Theme_5 in a Gradio space ~

Both of these themes have been updated to fix some of the long-standing inconsistencies ever since the transition to Gradio v5. Textboxes are no longer bright green and in-line code is readable now! Both themes are now visually identical across versions.

If your space is already using one of these themes, you just need to restart your space to get the latest version. No code changes needed.
Yosun 
posted an update 4 months ago
view post
Post
528
Is it possible to pay for more ZeroGPU usage quota?
·
osanseviero 
authored a paper 5 months ago
jxm 
posted an update 7 months ago
view post
Post
1122
New state-of-the-art BERT-size retrieval model: *cde-small-v2* 🥳🍾

Hi everyone! We at Cornell are releasing a new retrieval model this week. It uses the contextual embeddings framework, is based on ModernBERT backbone, and gets state-of-the-art results on the MTEB benchmark for its model size (140M parameters). cde-small-v2 gets an average score of 65.6 across the 56 datasets and sees improvements from our previous model in *every* task domain (retrieval, classification, etc.).

We made a lot of changes to make this model work. First of all, ModernBERT has a better tokenizer, which probably helped this work out-of-the-box. We also followed the principles from the CDE paper and used harder clusters and better hard-negative filtering, which showed a small performance improvement. And we made a few small changes that have been shown to work on the larger models: we disabled weight decay, masked out the prefix tokens during pooling, and added a residual connection from the first-stage to the second-stage for better gradient flow.

We're still looking for a computer sponsor to help us scale CDE to larger models. Since it's now state-of-the-art at the 100M parameter scale, it seems to be a reasonable bet that we could train a state-of-the-art large model if we had the GPUs. If you're interested in helping with this, please reach out!

Here's a link to the model: jxm/cde-small-v2
And here's a link to the paper: Contextual Document Embeddings (2410.02525)
akhaliq 
posted an update 8 months ago
view post
Post
26404
Google drops Gemini 2.0 Flash Thinking

a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more

now available in anychat, try it out: https://huggingface.co/spaces/akhaliq/anychat
·
lunarflu 
posted an update 8 months ago
akhaliq 
posted an update 9 months ago
akhaliq 
posted an update 9 months ago
akhaliq 
posted an update 9 months ago
MaximumEntropy 
authored a paper 10 months ago
lunarflu 
posted an update 12 months ago
lunarflu 
posted an update about 1 year ago
view post
Post
1985
Cool things this week from @huggingface !

🌎AI math olympiad winner NuminaMath is here!
🤗Announcing New Hugging Face and Keras NLP integration
✨UI overhaul to HF tokens!
🧊 Embed our dataset viewer on any webpage!

https://huggingface.co/blog/winning-aimo-progress-prize
https://huggingface.co/blog/keras-nlp-integration
https://huggingface.co/settings/tokens
https://x.com/julien_c/status/1812099420726456457

Check out the full list on our discord! 👇
https://discord.com/invite/JfAtkvEtRb
lunarflu 
posted an update about 1 year ago
view post
Post
2389
By popular demand, HF activity tracker v1.0 is here! 📊 let's build it together!🤗

Lots of things to improve, feel free to open PRs in the community tab!

good PR ideas:
- track more types of actions that include date+time
- bigger plot
- track discord activity too 🤯
- link github? ⚡

https://huggingface.co/spaces/huggingface-projects/LevelBot
  • 2 replies
·
akhaliq 
posted an update about 1 year ago
view post
Post
21071
Phased Consistency Model

Phased Consistency Model (2405.18407)

The consistency model (CM) has recently made significant progress in accelerating the generation of diffusion models. However, its application to high-resolution, text-conditioned image generation in the latent space (a.k.a., LCM) remains unsatisfactory. In this paper, we identify three key flaws in the current design of LCM. We investigate the reasons behind these limitations and propose the Phased Consistency Model (PCM), which generalizes the design space and addresses all identified limitations. Our evaluations demonstrate that PCM significantly outperforms LCM across 1--16 step generation settings. While PCM is specifically designed for multi-step refinement, it achieves even superior or comparable 1-step generation results to previously state-of-the-art specifically designed 1-step methods. Furthermore, we show that PCM's methodology is versatile and applicable to video generation, enabling us to train the state-of-the-art few-step text-to-video generator.
lunarflu 
posted an update about 1 year ago
view post
Post
2013
Weekly highlights for the HF ecosystem!

🚀 Phi 3
🦅 Falcon VLM
🤗 sentence-transformers v3.0 is here! Train and finetune embedding models with multi-GPU training, bf16 support, loss logging, callbacks and more!
🥳 Gradio launch event 6/6! We're launching 1.0 versions of two new libraries, Python + JS client libraries to programmatically query Gradio apps, and several new features making it easier to use Gradio apps in production!
✨ Tools now available in HuggingChat! Use any AI apps built by the community! 🔥
🧊 ML for 3D Course Unit 3 is here! Covering Gaussian splatting, how it fits in the generative 3D pipeline, and hands-on code to build your own demo!

See the full list here!
https://discord.com/channels/879548962464493619/897387888663232554/1245036889539612764 !
  • 2 replies
·
lunarflu 
posted an update about 1 year ago
view post
Post
2067
cooking up something....anyone interested in a daily activity tracker for HF?
·
akhaliq 
posted an update about 1 year ago
view post
Post
21277
Chameleon

Mixed-Modal Early-Fusion Foundation Models

Chameleon: Mixed-Modal Early-Fusion Foundation Models (2405.09818)

We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and an architectural parameterization tailored for the early-fusion, token-based, mixed-modal setting. The models are evaluated on a comprehensive range of tasks, including visual question answering, image captioning, text generation, image generation, and long-form mixed modal generation. Chameleon demonstrates broad and general capabilities, including state-of-the-art performance in image captioning tasks, outperforms Llama-2 in text-only tasks while being competitive with models such as Mixtral 8x7B and Gemini-Pro, and performs non-trivial image generation, all in a single model. It also matches or exceeds the performance of much larger models, including Gemini Pro and GPT-4V, according to human judgments on a new long-form mixed-modal generation evaluation, where either the prompt or outputs contain mixed sequences of both images and text. Chameleon marks a significant step forward in a unified modeling of full multimodal documents.
lunarflu 
posted an update about 1 year ago