Hugging Face's logo

Blog-explorers

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

eliebak  authored a paper 19 days ago
INTELLECT-1 Technical Report
eliebak  authored a paper 19 days ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Xenova  authored a paper 19 days ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
View all activity

blog-explorers's activity

samchain 
posted an update about 7 hours ago
view post
Post
467
NLP for economics 1.1 is out !

Following the 1.0 collection, I release the 1.1 version with an updated dataset for sentence similarity as well as a raw dataset from central bankers speeches.

The newest model is econo-sentence-v2 is a new version of a sentence-transformers model based on EconoBert ! It gets better results with a nuance on similarity.

If you're an economist looking for useful tools, don't hesitate to check it out !
mayank-mishra 
authored a paper 1 day ago
AtAndDev 
posted an update 10 days ago
nroggendorff 
posted an update 10 days ago
view post
Post
2778
hello, dev mode explorers!
  • 2 replies
·
potsawee 
authored 2 papers 11 days ago
mrzjy 
posted an update 11 days ago
view post
Post
1277
A very small project:

Introducing CreativeTinyZero:
mrzjy/Qwen2.5-1.5B-GRPO-Creative-Ad-Generation

Unlike the impressive DeepSeek-R1(-Zero), this project focuses on a pure reinforcement learning (RL) experiment applied to an open-domain task: creative advertisement generation.

Objective:

- To investigate the feasibility of applying R1-like methods to an open-domain task without a verifiable ground-truth reward, while at least demonstrating its potential.
- To explore whether <think> and <answer> rewards can be explicitly designed to provide strong guidance through RL based on human prior knowledge.

Note:
- Our goal is not to induce self-reflective thinking, but to align with human thought processes purely through RL, without any supervised fine-tuning (SFT) on any constructed dataset.

Despite its small size, the resulting 1.5B-GRPO model demonstrates intriguing generative capabilities—though it's still far from perfect.
  • 1 reply
·
nroggendorff 
posted an update 15 days ago
view post
Post
2638
Dearest None-yet Team,

I couldn't help but notice that our productivity has room for improvement. To address this, we will be engaging in a company-wide morale-building activity designed to boost teamwork, enthusiasm, and *most importantly* results.

I know you're all as excited as I am for this fun and absolutely required initiative. Participation is not just encouraged, it's mandatory. Think of it as a team-bonding experience you never signed up for but will absolutely tolerate.

More details to follow, but for now, mark your calendars and prepare for an engaging experience that will definitely make us all better, stronger, and more synchronized, or at least give us something to talk about later.

Looking forward to seeing you all there!

Best,
Me
·
Reality123b 
in blog-explorers/README 20 days ago

[Support] Community Articles

80
#5 opened 11 months ago by
victor
nroggendorff 
posted an update 21 days ago
view post
Post
1808
minor ui update, who dis?
  • 1 reply
·
julien-c 
in blog-explorers/README 21 days ago

[Support] Community Articles

80
#5 opened 11 months ago by
victor
victor 
in blog-explorers/README 26 days ago

[Support] Community Articles

80
#5 opened 11 months ago by
victor
AtAndDev 
posted an update 27 days ago
view post
Post
1874
everywhere i go i see his face
nroggendorff 
posted an update about 1 month ago
view post
Post
1583
to those complaining about the lack of private repo storage:
you can just use orgs, they have their own pool
  • 2 replies
·
AtAndDev 
posted an update about 1 month ago
view post
Post
524
Deepseek gang on fire fr fr
roseking 
posted an update about 1 month ago
view post
Post
328
📢 HuggingFace Daily Paper Newsletter (Multilingual)
🎯 Project Link: https://github.com/2404589803/hf-daily-paper-newsletter-multilingual
🌟 What is it?
An innovative open-source project that automatically collects the latest AI research papers from HuggingFace and translates them into multiple languages using InternLM-3, making cutting-edge AI research accessible to a global audience!
🚀 Key Features:
- 🤖 Automatic daily paper collection from HuggingFace
- 🌐 Supports 5 languages:
- 🇯🇵 Japanese
- 🇰🇷 Korean
- 🇪🇸 Spanish
- 🇫🇷 French
- 🇬🇧 English (original)
- ⚡ Powered by InternLM-3 for high-quality translations
- 🔄 Daily automated updates via GitHub Actions
- 📊 Structured JSON data format
- ⏰ Synchronized with Beijing time (UTC+8)
- 📝 Complete activity logging
🛠️ Technical Stack:
- Python
- InternLM-3 API
- GitHub Actions
- requests
- pytz
- openai
- gTTS
🔧 Easy Setup:
1. Clone the repository
2. Install dependencies with pip install -r requirements.txt
3. Set up your InternLM API key
4. Let GitHub Actions handle the rest!
📂 Data Organization:
- /Paper_metadata_download: Original English papers
- /Translated_papers:
- /ja: Japanese translations
- /ko: Korean translations
- /es: Spanish translations
- /fr: French translations
🤝 Powered By:
- [InternLM](https://internlm.org/) - Advanced translation model
- [HuggingFace](https://huggingface.co/) - Paper source
AtAndDev 
posted an update about 1 month ago
view post
Post
1608
R1 is out! And with a lot of other R1 releated models...
nroggendorff 
posted an update about 1 month ago
view post
Post
544
I just found out my GPU clock speed is 130MHz.
·
duyguislakoglu 
authored a paper about 1 month ago
nroggendorff 
posted an update about 1 month ago
view post
Post
1254
maybe a page where you can find open orgs to get started in collaboration with hf. i see so many people that dont have a direction.


i dont have ulterior motives, so dont ask
  • 1 reply
·