Post
894
We just crossed 1,500,000 public models on HF中国镜像站 (and 500k spaces, 330k datasets, 50k papers). One new repository is created every 15 seconds. Congratulations all!
- 1 reply
Nerdy Face
Enterprise
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nerdyface's activity
Post
808
Our new Agentic leaderboard is now live!💥
If you ever asked which LLM is best for powering agents, we've just made a leaderboard that ranks them all! Built with @albertvillanova , this ranks LLMs powering a smolagents CodeAgent on subsets of various benchmarks. ✅
🏆 GPT-4.5 comes on top, even beating reasoning models like DeepSeek-R1 or o1. And Claude-3.7-Sonnet is a close second!
The leaderboard also allows you to show the scores of vanilla LLMs (without any agentic setup) on the same benchmarks: this shows the huge improvements brought by agentic setups. 💪
(Note that results will be added manually, so the leaderboard might not always have the latest LLMs)
If you ever asked which LLM is best for powering agents, we've just made a leaderboard that ranks them all! Built with @albertvillanova , this ranks LLMs powering a smolagents CodeAgent on subsets of various benchmarks. ✅
🏆 GPT-4.5 comes on top, even beating reasoning models like DeepSeek-R1 or o1. And Claude-3.7-Sonnet is a close second!
The leaderboard also allows you to show the scores of vanilla LLMs (without any agentic setup) on the same benchmarks: this shows the huge improvements brought by agentic setups. 💪
(Note that results will be added manually, so the leaderboard might not always have the latest LLMs)
- 1 reply
Post
6994
I was chatting with
@peakji
, one of the cofounders of Manu AI, who told me he was on HF中国镜像站 (very cool!).
He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to the difference between GPT-3 and InstructGPT, some open-source foundation models are simply trained to 'answer everything in one response regardless of the complexity of the question' - after all, that's the user preference in chatbot use cases. Just a bit of post-training on agentic trajectories can make an immediate and dramatic difference.
As a thank you to the community, he shared 100 invite code first-come first serve, just use “HUGGINGFACE” to get access!
He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to the difference between GPT-3 and InstructGPT, some open-source foundation models are simply trained to 'answer everything in one response regardless of the complexity of the question' - after all, that's the user preference in chatbot use cases. Just a bit of post-training on agentic trajectories can make an immediate and dramatic difference.
As a thank you to the community, he shared 100 invite code first-come first serve, just use “HUGGINGFACE” to get access!
- 6 replies
Post
4642
10,000+ models based on Deepseek R1 have been publicly shared on HF中国镜像站! Which ones are your favorite ones: https://huggingface.co/models?sort=trending&search=r1. Truly game-changer!
Post
1017
🙋🏻♂️Hey there folks,
Did you know that you can use ModernBERT to detect model hallucinations ?
Check out the Demo : Tonic/hallucination-test
See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard
check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1
and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect
👆🏻if you like this topic please contribute code upstream 🚀
Did you know that you can use ModernBERT to detect model hallucinations ?
Check out the Demo : Tonic/hallucination-test
See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard
check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1
and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect
👆🏻if you like this topic please contribute code upstream 🚀
-
- 2 replies
taesiri
authored
a
paper
7 days ago
Post
649
Powered by
KRLabsOrg/lettucedect-large-modernbert-en-v1 from KRLabsOrg.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](https://huggingface.co/KRLabsOrg)
- **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](https://huggingface.co/KRLabsOrg)
- **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
Post
5871
Super happy to welcome Nvidia as our latest enterprise hub customer. They have almost 2,000 team members using HF中国镜像站, and close to 20,000 followers of their org. Can't wait to see what they'll open-source for all of us in the coming months!
Nvidia's org: https://huggingface.co/nvidia
Enterprise hub: https://huggingface.co/enterprise
Nvidia's org: https://huggingface.co/nvidia
Enterprise hub: https://huggingface.co/enterprise
Post
4731
We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones 🔥
Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.
To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.
🎯 For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an “AttributeTree” object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
📝 For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.
As a result, their system outperforms previous approaches by far!
As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 🏆
I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! 👉 SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys 👉 http://www.surveyx.cn/
Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.
To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.
🎯 For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an “AttributeTree” object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
📝 For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.
As a result, their system outperforms previous approaches by far!
As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 🏆
I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! 👉 SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys 👉 http://www.surveyx.cn/
Post
2822
What are the best organizations to follow on
@huggingface
?
On top of my head:
- Deepseek (35,000 followers): https://huggingface.co/deepseek-ai
- Meta Llama (27,000 followers): https://huggingface.co/meta-llama
- Black Forrest Labs (11,000 followers): https://huggingface.co/black-forest-labs
- OpenAI (5,000 followers): https://huggingface.co/openai
- Nvidia (16,000 followers): https://huggingface.co/nvidia
- MIcrosoft (9,000 followers): https://huggingface.co/microsoft
- AllenAI (2,000 followers): https://huggingface.co/allenai
- Mistral (5,000 followers): https://huggingface.co/mistralai
- XAI (600 followers): https://huggingface.co/xai-org
- Stability AI (16,000 followers): https://huggingface.co/stabilityai
- Qwen (16,000 followers): https://huggingface.co/Qwen
- GoogleAI (8,000 followers): https://huggingface.co/google
- Unsloth (3,000 followers): https://huggingface.co/unsloth
- Bria AI (4,000 followers): https://huggingface.co/briaai
- NousResearch (1,300 followers): https://huggingface.co/NousResearch
Bonus, the agent course org with 17,000 followers: https://huggingface.co/agents-course
On top of my head:
- Deepseek (35,000 followers): https://huggingface.co/deepseek-ai
- Meta Llama (27,000 followers): https://huggingface.co/meta-llama
- Black Forrest Labs (11,000 followers): https://huggingface.co/black-forest-labs
- OpenAI (5,000 followers): https://huggingface.co/openai
- Nvidia (16,000 followers): https://huggingface.co/nvidia
- MIcrosoft (9,000 followers): https://huggingface.co/microsoft
- AllenAI (2,000 followers): https://huggingface.co/allenai
- Mistral (5,000 followers): https://huggingface.co/mistralai
- XAI (600 followers): https://huggingface.co/xai-org
- Stability AI (16,000 followers): https://huggingface.co/stabilityai
- Qwen (16,000 followers): https://huggingface.co/Qwen
- GoogleAI (8,000 followers): https://huggingface.co/google
- Unsloth (3,000 followers): https://huggingface.co/unsloth
- Bria AI (4,000 followers): https://huggingface.co/briaai
- NousResearch (1,300 followers): https://huggingface.co/NousResearch
Bonus, the agent course org with 17,000 followers: https://huggingface.co/agents-course
- 1 reply
Post
3029
Less is More for Reasoning (LIMO): a 32B model fine-tuned with 817 examples can beat o1-preview on math reasoning! 🤯
Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT —no huge datasets or RL procedures needed.
Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.
⚡ The Less-is-More Reasoning Hypothesis:
‣ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
‣ Pre-training knowledge plus sufficient computational resources at inference levels up math skills
➡️ Core techniques:
‣ High-quality reasoning chains with self-verification steps
‣ 817 handpicked problems that encourage deeper reasoning
‣ Enough inference-time computation to allow extended reasoning
💪 Efficiency gains:
‣ Only 817 examples instead of 100k+
‣ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data
This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers 🚀
Read the full paper here 👉 LIMO: Less is More for Reasoning (2502.03387)
Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT —no huge datasets or RL procedures needed.
Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.
⚡ The Less-is-More Reasoning Hypothesis:
‣ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
‣ Pre-training knowledge plus sufficient computational resources at inference levels up math skills
➡️ Core techniques:
‣ High-quality reasoning chains with self-verification steps
‣ 817 handpicked problems that encourage deeper reasoning
‣ Enough inference-time computation to allow extended reasoning
💪 Efficiency gains:
‣ Only 817 examples instead of 100k+
‣ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data
This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers 🚀
Read the full paper here 👉 LIMO: Less is More for Reasoning (2502.03387)
taesiri
authored
a
paper
24 days ago
Post
3483
We crossed 1B+ tokens routed to inference providers partners on HF, that we released just a few days ago.
Just getting started of course but early users seem to like it & always happy to be able to partner with cool startups in the ecosystem.
Have you been using any integration and how can we make it better?
https://huggingface.co/blog/inference-providers
Just getting started of course but early users seem to like it & always happy to be able to partner with cool startups in the ecosystem.
Have you been using any integration and how can we make it better?
https://huggingface.co/blog/inference-providers
Post
5720
I was thinking i need to step up my game on training Flux LoRas models, time to have some fun ! ☀️
Expect a new drop per week on aesthetics that catched my attention, here are 3 of them that worked really well !
fffiloni/cute-comic-800
fffiloni/carbo-800
fffiloni/oniric-750
Expect a new drop per week on aesthetics that catched my attention, here are 3 of them that worked really well !
fffiloni/cute-comic-800
fffiloni/carbo-800
fffiloni/oniric-750
Post
2906
𝗚𝗿𝗲𝗮𝘁 𝗳𝗲𝗮𝘁𝘂𝗿𝗲 𝗮𝗹𝗲𝗿𝘁: you can now share agents to the Hub! 🥳🥳
And any agent pushed to Hub get a cool Space interface to directly chat with it.
This was a real technical challenge: for instance, serializing tools to export them meant that you needed to get all the source code for a tool, verify that it was standalone (not relying on external variables), and gathering all the packages required to make it run.
Go try it out! 👉 https://github.com/huggingface/smolagents
And any agent pushed to Hub get a cool Space interface to directly chat with it.
This was a real technical challenge: for instance, serializing tools to export them meant that you needed to get all the source code for a tool, verify that it was standalone (not relying on external variables), and gathering all the packages required to make it run.
Go try it out! 👉 https://github.com/huggingface/smolagents
- 2 replies
Post
2519
For those who haven't come across it yet, here's a handy trick to discuss an entire GitHub repo with an LLM:
=> Just replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs
=> Just replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs
Post
4823
"𝟮𝟬𝟮𝟱 𝘄𝗶𝗹𝗹 𝗯𝗲 𝘁𝗵𝗲 𝘆𝗲𝗮𝗿 𝗼𝗳 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀": this statement has often been made, here are numbers to support it.
I've plotted the progress of AI agents on GAIA test set, and it seems they're headed to catch up with the human baseline in early 2026.
And that progress is still driven mostly by the improvement of base LLMs: progress would be even faster with fine-tuned agentic models.
I've plotted the progress of AI agents on GAIA test set, and it seems they're headed to catch up with the human baseline in early 2026.
And that progress is still driven mostly by the improvement of base LLMs: progress would be even faster with fine-tuned agentic models.
Post
3737
𝗔𝗱𝘆𝗲𝗻'𝘀 𝗻𝗲𝘄 𝗗𝗮𝘁𝗮 𝗔𝗴𝗲𝗻𝘁𝘀 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 𝘀𝗵𝗼𝘄𝘀 𝘁𝗵𝗮𝘁 𝗗𝗲𝗲𝗽𝗦𝗲𝗲𝗸-𝗥𝟭 𝘀𝘁𝗿𝘂𝗴𝗴𝗹𝗲𝘀 𝗼𝗻 𝗱𝗮𝘁𝗮 𝘀𝗰𝗶𝗲𝗻𝗰𝗲 𝘁𝗮𝘀𝗸𝘀! ❌
➡️ How well do reasoning models perform on agentic tasks? Until now, all indicators seemed to show that they worked really well. On our recent reproduction of Deep Search, OpenAI's o1 was by far the best model to power an agentic system.
So when our partner Adyen built a huge benchmark of 450 data science tasks, and built data agents with smolagents to test different models, I expected reasoning models like o1 or DeepSeek-R1 to destroy the tasks at hand.
👎 But they really missed the mark. DeepSeek-R1 only got 1 or 2 out of 10 questions correct. Similarly, o1 was only at ~13% correct answers.
🧐 These results really surprised us. We thoroughly checked them, we even thought our APIs for DeepSeek were broken and colleagues Leandro Anton helped me start custom instances of R1 on our own H100s to make sure it worked well.
But there seemed to be no mistake. Reasoning LLMs actually did not seem that smart. Often, these models made basic mistakes, like forgetting the content of a folder that they had just explored, misspelling file names, or hallucinating data. Even though they do great at exploring webpages through several steps, the same level of multi-step planning seemed much harder to achieve when reasoning over files and data.
It seems like there's still lots of work to do in the Agents x Data space. Congrats to Adyen for this great benchmark, looking forward to see people proposing better agents! 🚀
Read more in the blog post 👉 https://huggingface.co/blog/dabstep
➡️ How well do reasoning models perform on agentic tasks? Until now, all indicators seemed to show that they worked really well. On our recent reproduction of Deep Search, OpenAI's o1 was by far the best model to power an agentic system.
So when our partner Adyen built a huge benchmark of 450 data science tasks, and built data agents with smolagents to test different models, I expected reasoning models like o1 or DeepSeek-R1 to destroy the tasks at hand.
👎 But they really missed the mark. DeepSeek-R1 only got 1 or 2 out of 10 questions correct. Similarly, o1 was only at ~13% correct answers.
🧐 These results really surprised us. We thoroughly checked them, we even thought our APIs for DeepSeek were broken and colleagues Leandro Anton helped me start custom instances of R1 on our own H100s to make sure it worked well.
But there seemed to be no mistake. Reasoning LLMs actually did not seem that smart. Often, these models made basic mistakes, like forgetting the content of a folder that they had just explored, misspelling file names, or hallucinating data. Even though they do great at exploring webpages through several steps, the same level of multi-step planning seemed much harder to achieve when reasoning over files and data.
It seems like there's still lots of work to do in the Agents x Data space. Congrats to Adyen for this great benchmark, looking forward to see people proposing better agents! 🚀
Read more in the blog post 👉 https://huggingface.co/blog/dabstep
Post
9775
Introducing 𝗼𝗽𝗲𝗻 𝗗𝗲𝗲𝗽-𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 by HF中国镜像站! 💥
OpenAI's latest agentic app Deep Research seems really good... But it's closed, as usual.
⏱️ So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! ⏱️
➡️ We built open-Deep-Research, an entirely open agent that can: navigate the web autonomously, scroll and search through pages, download and manipulate files, run calculation on data...
We aimed for the best performance: are the agent's answers really rigorous?
On GAIA benchmark, Deep Research had 67% accuracy on the validation set.
➡️ open Deep Research is at 55% (powered by o1), it is:
- the best pass@1 solution submitted
- the best open solution 💪💪
And it's only getting started ! Please jump in, drop PRs, and let's bring it to the top !
Read the blog post 👉 https://huggingface.co/blog/open-deep-research
OpenAI's latest agentic app Deep Research seems really good... But it's closed, as usual.
⏱️ So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! ⏱️
➡️ We built open-Deep-Research, an entirely open agent that can: navigate the web autonomously, scroll and search through pages, download and manipulate files, run calculation on data...
We aimed for the best performance: are the agent's answers really rigorous?
On GAIA benchmark, Deep Research had 67% accuracy on the validation set.
➡️ open Deep Research is at 55% (powered by o1), it is:
- the best pass@1 solution submitted
- the best open solution 💪💪
And it's only getting started ! Please jump in, drop PRs, and let's bring it to the top !
Read the blog post 👉 https://huggingface.co/blog/open-deep-research
Post
2357
🙋🏻♂️hey there folks ,
Goedel's Theorem Prover is now being demo'ed on huggingface : Tonic/Math
give it a try !
Goedel's Theorem Prover is now being demo'ed on huggingface : Tonic/Math
give it a try !