Hugging Face's logo

Dev Mode Explorers

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

vwxyzjn  authored a paper about 23 hours ago
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization
vwxyzjn  authored a paper about 23 hours ago
A2C is a special case of PPO
vwxyzjn  authored a paper about 23 hours ago
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
View all activity

dev-mode-explorers's activity

MoritzLaurer 
posted an update about 5 hours ago
view post
Post
249
🚀 Releasing a new zeroshot-classifier based on ModernBERT! Some key takeaways:

- ⚡ Speed & efficiency: It's multiple times faster and uses significantly less memory than DeBERTav3. You can use larger batch sizes and enabling bf16 (instead of fp16) gave me a ~2x speed boost as well
- 📉 Performance tradeoff: It performs slightly worse than DeBERTav3 on average across my zeroshot classification task collection
- 🧠 Use cases: I recommend using it for scenarios requiring speed and a larger context window (8k).
- 💡 What’s next? I’m preparing a newer version trained on better + longer synthetic data to fully leverage the 8k context window and improve upon the training mix of my older zeroshot-v2.0 models. I also hope that there will be a multilingual variant in the future.

Great work by https://huggingface.co/answerdotai !

If you’re looking for a high-speed zeroshot classifier, give it a try!

📄 Resources below: 👇
Base model: MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Large model: MoritzLaurer/ModernBERT-large-zeroshot-v2.0
Updated zeroshot collection: MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f
ModernBERT collection with paper: answerdotai/modernbert-67627ad707a4acbf33c41deb
vwxyzjn 
authored 5 papers about 23 hours ago
DamarJati 
posted an update 6 days ago
view post
Post
2104
Happy New Year 2025 🤗
For the Huggingface community.
merve 
posted an update 6 days ago
view post
Post
4165
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
alielfilali01 
posted an update 8 days ago
view post
Post
1727
~75% on the challenging GPQA with only 40M parameters 🔥🥳

GREAT ACHIEVEMENT ! Or is it ?

This new Work, "Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation", take out the mystery about many models i personally suspected their results. Speacially on leaderboards other than the english one, Like the Open Arabic LLM Leaderbaord OALL/Open-Arabic-LLM-Leaderboard.

The authors of this work, first started by training a model on the GPQA data, which, unsurprisingly, led to the model achieving 100% performance.

Afterward, they trained what they referred to as a 'legitimate' model on legitimate data (MedMCQA). However, they introduced a distillation loss from the earlier, 'cheated' model.

What they discovered was fascinating: the knowledge of GPQA leaked through this distillation loss, even though the legitimate model was never explicitly trained on GPQA during this stage.

This raises important questions about the careful use of distillation in model training, especially when the training data is opaque. As they demonstrated, it’s apparently possible to (intentionally or unintentionally) leak test data through this method.

Find out more: Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation (2412.15255)
  • 1 reply
·
merve 
posted an update 13 days ago
ehristoforu 
posted an update 15 days ago
view post
Post
2891
✒️ Ultraset - all-in-one dataset for SFT training in Alpaca format.
fluently-sets/ultraset

❓ Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.

🤯 Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.

🤗 For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.

❇️ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
Abhaykoul 
posted an update 17 days ago
view post
Post
1639
🔥 BIG ANNOUNCEMENT: THE HELPINGAI API IS LIVE! 🔥

Yo, the moment you’ve all been waiting for is here! 🚀 The HelpingAI API is now LIVE and ready to level up your projects! 🔥 We’re bringing that next-level AI goodness straight to your fingertips. 💯

No more waiting— it’s time to build something epic! 🙌

From now on, you can integrate our cutting-edge AI models into your own applications, workflows, and everything in between. Whether you’re a developer, a creator, or just someone looking to make some serious moves, this is your chance to unlock the full potential of emotional intelligence and adaptive AI.

Check out the docs 🔥 and let’s get to work! 🚀

👉 Check out the docs and start building (https://helpingai.co/docs)
👉 Visit the HelpingAI website (https://helpingai.co/)
·
MoritzLaurer 
posted an update 17 days ago
view post
Post
2549
Quite excited by the ModernBERT release! 0.15/0.4B small, 2T modern pre-training data and tokenizer with code, 8k context window, great efficient model for embeddings & classification!

This will probably be the basis for many future SOTA encoders! And I can finally stop using DeBERTav3 from 2021 :D

Congrats @answerdotai , @LightOnIO and collaborators like @tomaarsen !

Paper and models here 👇https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb
·
fdaudens 
posted an update 18 days ago
view post
Post
1269
🔍 From instruction-following to creative storytelling, dive into 2024's most impactful AI datasets! These gems are shaping everything from scientific research to video understanding.

Check it out: huggingface/open-source-ai-year-in-review-2024
m-ric 
posted an update 18 days ago
view post
Post
2007
After 6 years, BERT, the workhorse of encoder models, finally gets a replacement: 𝗪𝗲𝗹𝗰𝗼𝗺𝗲 𝗠𝗼𝗱𝗲𝗿𝗻𝗕𝗘𝗥𝗧! 🤗

We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models.

The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs).

It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs.

Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub.

➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT.

𝗧𝗟;𝗗𝗥:
🏛️ Architecture changes:
⇒ First, standard modernizations:
- Rotary positional embeddings (RoPE)
- Replace GeLU with GeGLU,
- Use Flash Attention 2
✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead.

🥇 As a result, the model tops the game of encoder models:
It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster!

Read the blog post 👉 https://huggingface.co/blog/modernbert
  • 1 reply
·
m-ric 
posted an update 19 days ago
view post
Post
2391
𝐇𝐮𝐠𝐠𝐢𝐧𝐠 𝐅𝐚𝐜𝐞 𝐫𝐞𝐥𝐞𝐚𝐬𝐞𝐬 𝐏𝐢𝐜𝐨𝐭𝐫𝐨𝐧, 𝐚 𝐦𝐢𝐜𝐫𝐨𝐬𝐜𝐨𝐩𝐢𝐜 𝐥𝐢𝐛 𝐭𝐡𝐚𝐭 𝐬𝐨𝐥𝐯𝐞𝐬 𝐋𝐋𝐌 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝟒𝐃 𝐩𝐚𝐫𝐚𝐥𝐥𝐞𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 🥳

🕰️ Llama-3.1-405B took 39 million GPU-hours to train, i.e. about 4.5 thousand years.

👴🏻 If they had needed all this time, we would have GPU stories from the time of Pharaoh 𓂀: "Alas, Lord of Two Lands, the shipment of counting-stones arriving from Cathay was lost to pirates, this shall delay the building of your computing temple by many moons "

🛠️ But instead, they just parallelized the training on 24k H100s, which made it take just a few months.
This required parallelizing across 4 dimensions: data, tensor, context, pipeline.
And it is infamously hard to do, making for bloated code repos that hold together only by magic.

🤏 𝗕𝘂𝘁 𝗻𝗼𝘄 𝘄𝗲 𝗱𝗼𝗻'𝘁 𝗻𝗲𝗲𝗱 𝗵𝘂𝗴𝗲 𝗿𝗲𝗽𝗼𝘀 𝗮𝗻𝘆𝗺𝗼𝗿𝗲! Instead of building mega-training codes, Hugging Face colleagues cooked in the other direction, towards tiny 4D parallelism libs. A team has built Nanotron, already widely used in industry.
And now a team releases Picotron, a radical approach to code 4D Parallelism in just a few hundred lines of code, a real engineering prowess, making it much easier to understand what's actually happening!

⚡ 𝗜𝘁'𝘀 𝘁𝗶𝗻𝘆, 𝘆𝗲𝘁 𝗽𝗼𝘄𝗲𝗿𝗳𝘂𝗹:
Counting in MFU (Model FLOPs Utilization, how much the model actually uses all the compute potential), this lib reaches ~50% on SmolLM-1.7B model with 8 H100 GPUs, which is really close to what huge libs would reach. (Caution: the team is leading further benchmarks to verify this)

Go take a look 👉 https://github.com/huggingface/picotron/tree/main/picotron
  • 1 reply
·
freddyaboulton 
posted an update 19 days ago
fdaudens 
posted an update 19 days ago
view post
Post
1229
🤝 Want to share your AI models while protecting your work? Licenses are key!

Fascinating to see that nearly 60% of models on the Hub use Apache & MIT licenses.

Explore the viz here: huggingface/open-source-ai-year-in-review-2024
jbilcke-hf 
posted an update 19 days ago
view post
Post
3412
Doing some testing with HunyuanVideo on the Hugging Face Inference Endpoints 🤗

prompt: "a Shiba Inu is acting as a DJ, he wears sunglasses and is mixing and scratching with vinyl discs at a Ibiza sunny sand beach party"

1280x720, 22 steps, 121 frames

There are still some things to iron out regarding speed and memory usage, right now it takes 20min on an A100 (see attached charts)

but you can check it out here:

https://huggingface.co/jbilcke-hf/HunyuanVideo-for-InferenceEndpoints

There are various things I want to try like the 100% diffusers version and other models (LTX-Video..)
AtAndDev 
posted an update 19 days ago
view post
Post
378
@s3nh Hey man check your discord! Got some news.
  • 4 replies
·