Hugging Face's logo

BigScience Biomedical Datasets

non-profit
Activity Feed Request to join this org

AI & ML interests

We aim to unify the schema across many different biomedical NLP resources.

Recent Activity

jfries  new activity 28 days ago
bigbio/bc5cdr:Annotation Guideline URL not availabel
jfries  updated a dataset 28 days ago
bigbio/bc5cdr
phlobo  updated a dataset 2 months ago
bigbio/craft
View all activity

bigbio's activity

ImranzamanML 
posted an update about 20 hours ago
view post
Post
1069
Hugging Face just launched the AI Agents Course – a free journey from beginner to expert in AI agents!

- Learn AI Agent fundamentals, use cases and frameworks
- Use top libraries like LangChain & LlamaIndex
- Compete in challenges & earn a certificate
- Hands-on projects & real-world applications

https://huggingface.co/learn/agents-course/unit0/introduction

You can join for a live Q&A on Feb 12 at 5PM CET to learn more about the course here

https://www.youtube.com/live/PopqUt3MGyQ
prithivMLmods 
posted an update 3 days ago
view post
Post
3573
QwQ Edge Gets a Small Update..! 💬
try now: prithivMLmods/QwQ-Edge

🚀Now, you can use the following commands for different tasks:

🖼️ @image 'prompt...' → Generates an image
🔉@tts1 'prompt...' → Generates speech in a female voice
🔉 @tts2 'prompt...' → Generates speech in a male voice
🅰️@text 'prompt...' → Enables textual conversation (If not specified, text-to-text generation is the default mode)

💬Multimodality Support : prithivMLmods/Qwen2-VL-OCR-2B-Instruct
💬For text generation, the FastThink-0.5B model ensures quick and efficient responses, prithivMLmods/FastThink-0.5B-Tiny
💬Image Generation: sdxl lightning model, SG161222/RealVisXL_V4.0_Lightning

Github: https://github.com/PRITHIVSAKTHIUR/QwQ-Edge

graph TD
    A[User Interface] --> B[Chat Logic]
    B --> C{Command Type}
    C -->|Text| D[FastThink-0.5B]
    C -->|Image| E[Qwen2-VL-OCR-2B]
    C -->|@image| F[Stable Diffusion XL]
    C -->|@tts| G[Edge TTS]
    D --> H[Response]
    E --> H
    F --> H
    G --> H
mkurman 
posted an update 4 days ago
view post
Post
1462
Blurred-Thoughts Supervised-Finetuning 🙈

After hours of working with GitHub Copilot to organize the code, I'm keen to announce the release of Blurred Thoughts Supervised-Finetuning (BT-SFT), a new method for fine-tuning LLMs to produce more diverse and creative responses.

BT-SFT introduces:
✅ Smart tokenization method randomly masks tokens within <think> ... </think> tags, promoting the model to generate diverse responses that align better with its probability distribution instead of memorizing the thought process from distilled data.
✅ Reward function that ensures responses are well-structured.

Explore and contribute to the project available in my GitHub repository:
https://github.com/mkurman/blurred-thoughts-SFT

Keep me updated on your experiments with BT-SFT! 🐐
rmayormartins 
posted an update 4 days ago
view post
Post
464
🌎 Join Latin American AI Developers Organization!
Share your AI work and connect with developers across Latin America! We welcome:
Spaces/Datasets/Models
Visit our Space: AI Developers from Latin America Community https://huggingface.co/LatinAI
_________________________________
🌎 ¡Únete a la Organizacion de Desarrolladores de IA de América Latina!
¡Comparte tu trabajo en IA y conecta con desarrolladores de toda Latinoamérica! Buscamos:
Spaces/Datasets/Modelos
Visita nuestro Space: AI Developers from Latin America Community https://huggingface.co/LatinAI
#LatinAmerica #AI #MachineLearning #HuggingFace #LatAm
albertvillanova 
posted an update 7 days ago
view post
Post
2930
🚀 Introducing @huggingface Open Deep-Research💥

In just 24 hours, we built an open-source agent that:
✅ Autonomously browse the web
✅ Search, scroll & extract info
✅ Download & manipulate files
✅ Run calculations on data

55% on GAIA validation set! Help us improve it!💡
https://huggingface.co/blog/open-deep-research
  • 3 replies
·
Tonic 
posted an update 8 days ago
view post
Post
1974
🙋🏻‍♂️hey there folks ,

Goedel's Theorem Prover is now being demo'ed on huggingface : Tonic/Math

give it a try !
prithivMLmods 
posted an update 9 days ago
view post
Post
4732
o3-Mini and Deepseek R1
Worked out with some famous and weird examples.

🔥Blog: https://huggingface.co/blog/prithivMLmods/o3-mini-vs-deepseek-r1

Prompt : Using HTML, CSS, and JavaScript in a single HTML file to create a simulation of the solar system. Pay extreme attention to the UI to make it as intuitive as possible. Ensure that every planet appears as a sphere and is labeled with its corresponding name.

example 1: o3 Mini , example 2: Deepseek R1

Q2 : https://huggingface.co/blog/prithivMLmods/o3-mini-vs-deepseek-r1#q2--web-solar-system-explorer
  • 1 reply
·
mkurman 
posted an update 12 days ago
view post
Post
2030
Blurred-Thoughts Supervised Fine-Tuning (BT-SFT) 🤖

Can we teach a model to think completely on its own without reinforcement learning? Actually, yes.

We can do straightforward supervised fine-tuning using a relatively simple trick: blurring a part of CoT thoughts. But why is this effective?

We observed that various models differ in their thinking processes, and fine-tuning one model on another model’s thoughts (CoT) can sometimes be inefficient—often resulting in the model simply memorizing reasoning rather than learning how to actually think.

I discovered that this process can still be efficient if we clearly indicate when the model should start and stop thinking and uncover only a part of CoT and the expected answer, blurring the other part of CoT. This approach allows the model to learn only a portion of the thought process while still arriving at an expected answer.

To demonstrate this, you can watch my experimental BT-SFT on meditsolutions/Llama-3.2-SUN-2.5B-chat model, which was fine-tuned on 151 million tokens from the Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B dataset.

Enjoy! 🚀

PS. If you were curious enough to read this, leave me a comment. It's always nice to chat with open-minded and intelligent ppl.
  • 3 replies
·
not-lain 
posted an update 13 days ago
mkurman 
posted an update 13 days ago
view post
Post
2755
Ok, my 14B DeepSeek R1 merge with Qwen2.5 1M is really hot right now—it's got 2.6k downloads! It's sitting pretty as the top trending model on the third page. 🔥

Check it out if you haven't already!
mkurman/Qwen2.5-14B-DeepSeek-R1-1M
·
AtAndDev 
posted an update 13 days ago
view post
Post
1841
everywhere i go i see his face
prithivMLmods 
posted an update 13 days ago
view post
Post
5097
Deepswipe by
.
.
.
. Deepseek🐬🗿






Everything is now in recovery. 📉📈
·
Tonic 
posted an update 14 days ago
view post
Post
2865
🙋🏻‍♂️ Hey there folks ,

our team made a game during the @mistral-game-jam and we're trying to win the community award !

try our game out and drop us a ❤️ like basically to vote for us !

Mistral-AI-Game-Jam/TextToSurvive

hope you like it !
mmaguero 
posted an update 15 days ago
view post
Post
1486
🚀 Multidimensional Affective Analysis for Guarani/Jopara! 🌎

This project explored affective computing for low-resource languages, focusing on emotion recognition, humor detection, and offensive language identification in Guarani and Jopara (a code-switching mix of Guarani and Spanish).

Highlights:
🧵 Corpora:
- Emotion Recognition
- Humor Detection
- Offensive Language Identification
💻 Base Models for Fine-Tuning (trained on Guarani Wiki):
- From scratch: BERT-based tiny, small, base and large models
- Continuously pre-trained models: Multilingual-BERT and BETO
📓 Baseline Notebooks:
- Fine-tuning BERT-based models
- NCRF++ models via GitHub

💡 Check the repo!
https://github.com/mmaguero/guarani-multi-affective-analysis

📖 Check out the publication here:
- https://digibug.ugr.es/handle/10481/98843
- https://link.springer.com/article/10.1007/s12559-023-10165-0

#NLP #AffectiveComputing #LowResourceLanguages #Guarani #Jopara #SentimentAnalysis #AIForAll
mkurman 
posted an update 16 days ago
view post
Post
1912
I’ve simplified things for the AI OS community!

Check out Qwen-2.5-14B-DeepSeek-R1-1M! This one's a cool blend of the latest Qwen 2.5 with 14 billion parameters and has a massive 1 million token context window. It also comes with the DeepSeek R1 version of the Qwen 2.5 14B base model.

Enjoy! 🚀

mkurman/Qwen2.5-14B-DeepSeek-R1-1M
AtAndDev 
posted an update 20 days ago
view post
Post
514
Deepseek gang on fire fr fr
prithivMLmods 
posted an update 22 days ago
AtAndDev 
posted an update 22 days ago
view post
Post
1601
R1 is out! And with a lot of other R1 releated models...
mkurman 
posted an update 25 days ago
not-lain 
posted an update 25 days ago
view post
Post
1563
we now have more than 2000 public AI models using ModelHubMixin🤗