Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence
Paper
•
2503.05037
•
Published
•
4
Spaces-explorers
AI & ML interests
Contributors who are invited to beta-test our next big feature! Contact us if you want to join this team :-)
Recent Activity
View all activity
spaces-explorers's activity
mohsenfayyaz
authored
a
paper
14 days ago
nguyenvulebinh
authored
a
paper
28 days ago
Post
4360
Hey everyone, we've given https://hf.co/spaces page a fresh update!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
- 5 replies
Post
3070
Finally, an open-source AI that turns your lyrics into full songs is here—meet YuE! Unlike other tools that only create short clips, YuE can make entire songs (up to 5 minutes) with vocals, melody, and instruments all working together. Letsss go!
m-a-p/YuE-s1-7B-anneal-en-cot
m-a-p/YuE-s1-7B-anneal-en-cot
Post
563
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)
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)
Post
2217
Qwen/QwQ-32B-Preview shows us the future (and it's going to be exciting)...
I tested it against some really challenging reasoning prompts and the results are amazing 🤯.
Check this dataset for the results: victor/qwq-misguided-attention
I tested it against some really challenging reasoning prompts and the results are amazing 🤯.
Check this dataset for the results: victor/qwq-misguided-attention
- 2 replies
Post
2605
Perfect example of why
Qwen/Qwen2.5-Coder-32B-Instruct is insane?
Introducing: AI Video Composer 🔥
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 🚀.
Introducing: AI Video Composer 🔥
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 🚀.
Post
1849
Qwen2.5-72B is now the default HuggingChat model.
This model is so good that you must try it! I often get better results on rephrasing with it than Sonnet or GPT-4!!
This model is so good that you must try it! I often get better results on rephrasing with it than Sonnet or GPT-4!!
Post
1677
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF is now available in HuggingChat if you want to try it!
https://huggingface.co/chat/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
https://huggingface.co/chat/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Post
2684
NEW - Inference Playground
Maybe like me you have always wanted a super easy way to compare llama3.2-1B vs. llama3.2-3B? or the same model with different temperatures?
Trying and comparing warm Inference API models has never been easier!
Just go to https://hf.co/playground, set your token and you're ready to go.
We'll keep improving, feedback welcome 😊
Maybe like me you have always wanted a super easy way to compare llama3.2-1B vs. llama3.2-3B? or the same model with different temperatures?
Trying and comparing warm Inference API models has never been easier!
Just go to https://hf.co/playground, set your token and you're ready to go.
We'll keep improving, feedback welcome 😊
- 2 replies
Post
4517
Hello everybody,
We've rolled out a major update to ZeroGPU! All the Spaces are now running on it.
Major improvements:
1. GPU cold starts about twice as fast!
2. RAM usage reduced by two-thirds, allowing more effective resource usage, meaning more GPUs for the community!
3. ZeroGPU initializations (coldstarts) can now be tracked and displayed (use
4. Improved compatibility and PyTorch integration, increasing ZeroGPU compatible spaces without requiring any modifications!
Feel free to answer in the post if you have any questions
🤗 Best regards,
Charles
We've rolled out a major update to ZeroGPU! All the Spaces are now running on it.
Major improvements:
1. GPU cold starts about twice as fast!
2. RAM usage reduced by two-thirds, allowing more effective resource usage, meaning more GPUs for the community!
3. ZeroGPU initializations (coldstarts) can now be tracked and displayed (use
progress=gr.Progress(track_tqdm=True))4. Improved compatibility and PyTorch integration, increasing ZeroGPU compatible spaces without requiring any modifications!
Feel free to answer in the post if you have any questions
🤗 Best regards,
Charles
Post
2878
Sharing for anyone using Diffusers
If you have
If you do not have the model repo saved in your cache, then automatically inferring the pipeline config will not work since the reference repo
You can use an alternative SD1.5 repo id to still configure your pipeline.
We're working on resolving the issue ASAP.
from_single_file loading and affected by the Runway SD 1.5 issue.If you have
runwayml/stable-diffusion-v1-5 saved locally in your HF cache then loading single file checkpoints in the following way should still work. from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_single_file("<url or path to single file checkpoint>")If you do not have the model repo saved in your cache, then automatically inferring the pipeline config will not work since the reference repo
runwayml/stable-diffusion-v1-5 doesn't exist anymore. You can use an alternative SD1.5 repo id to still configure your pipeline.
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_single_file("<url or path to single file checkpoint>", config="Lykon/DreamShaper")We're working on resolving the issue ASAP.
-
- 2 replies
Post
5839
🙋 Calling all Hugging Face users! We want to hear from YOU!
What feature or improvement would make the biggest impact on Hugging Face?
Whether it's the Hub, better documentation, new integrations, or something completely different – we're all ears!
Your feedback shapes the future of Hugging Face. Drop your ideas in the comments below! 👇
What feature or improvement would make the biggest impact on Hugging Face?
Whether it's the Hub, better documentation, new integrations, or something completely different – we're all ears!
Your feedback shapes the future of Hugging Face. Drop your ideas in the comments below! 👇
- 182 replies
Post
4141
How good are you at spotting AI-generated images?
Find out by playing Fake Insects 🐞 a Game where you need to identify which insects are fake (AI generated). Good luck & share your best score in the comments!
victor/fake-insects
Find out by playing Fake Insects 🐞 a Game where you need to identify which insects are fake (AI generated). Good luck & share your best score in the comments!
victor/fake-insects
- 6 replies
nguyenvulebinh
authored
a
paper
8 months ago
Post
4057
Hugging Face famous organisations activity. Guess which one has the word "Open" in it 😂
- 2 replies
Post
2213
Hi
@jonoirwin
! Big fan of https://fastvoiceagent.cerebrium.ai/ 🔥
I'd be super happy to give you a GPU grant to host it on a Space, it would allow more people to discover and use it!
I'd be super happy to give you a GPU grant to host it on a Space, it would allow more people to discover and use it!
-
- 1 reply
Post
4018
Together MoA is a really interesting approach based on open source models!
"We introduce Mixture of Agents (MoA), an approach to harness the collective strengths of multiple LLMs to improve state-of-the-art quality. And we provide a reference implementation, Together MoA, which leverages several open-source LLM agents to achieve a score of 65.1% on AlpacaEval 2.0, surpassing prior leader GPT-4o (57.5%)."
Read more here: https://www.together.ai/blog/together-moa
PS: they provide some demo code: (https://github.com/togethercomputer/MoA/blob/main/bot.py) - if someone release a Space for it it could go 🚀
"We introduce Mixture of Agents (MoA), an approach to harness the collective strengths of multiple LLMs to improve state-of-the-art quality. And we provide a reference implementation, Together MoA, which leverages several open-source LLM agents to achieve a score of 65.1% on AlpacaEval 2.0, surpassing prior leader GPT-4o (57.5%)."
Read more here: https://www.together.ai/blog/together-moa
PS: they provide some demo code: (https://github.com/togethercomputer/MoA/blob/main/bot.py) - if someone release a Space for it it could go 🚀
- 1 reply
Post
2402
Congrats to
@alvdansen
for one of the nicest SD LoRA ever. It's so sharp and beautiful!
Check the model page to try it on your own prompts: alvdansen/BandW-Manga
And follow @alvdansen for more 😙
Check the model page to try it on your own prompts: alvdansen/BandW-Manga
And follow @alvdansen for more 😙
-
-
- 5 replies
Post
1860
> We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024). (90.9% vs 90.2%).
@Bin12345 interested in a ZeroGPU Spaces for Bin12345/AutoCoder
@Bin12345 interested in a ZeroGPU Spaces for Bin12345/AutoCoder
-
- 6 replies