Hugging Face's logo

HuggingFaceM4
Enterprise
company
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

lewtun  new activity 4 days ago
HuggingFaceM4/FineVision:Design choice for Q&A token length
lusxvr  new activity 4 days ago
HuggingFaceM4/FineVision:Design choice for Q&A token length
lusxvr  new activity 4 days ago
HuggingFaceM4/FineVision:Breaking lines for visibility
View all activity

merve 
posted an update about 1 hour ago
merve 
posted an update 1 day ago
jbilcke-hf 
posted an update 3 days ago
view post
Post
432
Did you know you can use AI-Toolkit by Ostris (https://github.com/ostris/ai-toolkit) to train AI image and video models directly inside a Hugging Face space?

The benefit of doing so is that you will get a nice UI, if you do not want to deal with JSON files and CLI shenanigans!

I have created a ready-to-use template you can deploy to your own HF Space to train generative models in a few clicks.

All you have to do is to duplicate my space to your private space by going here: jbilcke-hf/ai-toolkit

This space requires a good GPU and most importantly a persistent storage, as everything is stored in /data.

Currently multiple GPUs isn't supported yet in the UI but it is planned(https://discord.com/channels/1144033039786188891/1166417204015808603/1404851082361835623)

P.S.: Don't forget to set your space to private to make sure only you can access, delete and run training jobs!
  • 1 reply
·
lewtun 
in HuggingFaceM4/FineVision 4 days ago

Design choice for Q&A token length

2
#1 opened 4 days ago by
lewtun
lusxvr 
in HuggingFaceM4/FineVision 4 days ago

Design choice for Q&A token length

2
#1 opened 4 days ago by
lewtun

Breaking lines for visibility

❤️ 1
#2 opened 4 days ago by
ariG23498
ariG23498 
in HuggingFaceM4/FineVision 4 days ago

Breaking lines for visibility

❤️ 1
#2 opened 4 days ago by
ariG23498
tfrere 
updated a Space 4 days ago
lusxvr 
updated a Space 4 days ago
lusxvr 
updated a dataset 5 days ago
lusxvr 
in HuggingFaceM4/FineVision 5 days ago

Update README.md

1
#10 opened 5 days ago by
speed
lusxvr 
published a Space 5 days ago
lusxvr 
published 2 datasets 5 days ago
lusxvr 
updated a dataset 6 days ago
davanstrien 
posted an update 6 days ago
view post
Post
361
I fine-tuned a smol VLM to generate specialized art history metadata!

davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)

Trained with TRL + HF Jobs - single UV script, no GPU needed!

Space to explore predictions on a test set: davanstrien/iconclass-predictions

Blog soon!
merve 
posted an update 8 days ago
view post
Post
6028
large AI labs have dropped so many open models last week 🔥 don't miss out on them

→ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
→ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
→ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B

find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
  • 1 reply
·
giadap 
posted an update 8 days ago
view post
Post
290
I've noticed something. While we're careful about what we post on social media, we're sharing our deepest and most intimate thoughts with AI chatbots -- health concerns, financial worries, relationship issues, business ideas...

With OpenAI hinting at ChatGPT advertising, this matters more than ever. Unlike banner ads, AI advertising happens within the conversation itself. Sponsors could subtly influence that relationship advice or financial guidance.

The good news? We have options.
🤝 Open source AI models let us keep conversations private, avoid surveillance-based business models, and build systems that actually serve users first.

Read more about it in our latest blog post, co-written with
@frimelle
https://huggingface.co/blog/giadap/privacy-conversational-ai
dylanebert 
posted an update 12 days ago
view post
Post
2840
These are the current best Generative 3D

Render:
#1 - CSM
#2 - TRELLIS (open-source)
#3 - Zaohaowu3D

Topology:
#1 - Hunyuan3D-2
#2 - TRELLIS (open-source)
#3 - Hunyuan3D-2.1

as voted/submitted openly on dylanebert/3d-arena
giadap 
posted an update 12 days ago
view post
Post
294
📊 We benchmark models for coding, reasoning, or safety… but what about companionship?

At Hugging Face, we’ve been digging into this question because many of you know how deeply I care about how people build emotional bonds with AI.

That’s why, building on our ongoing research, my amazing co-author and colleague @frimelle created the AI Companionship Leaderboard 🦾
frimelle/companionship-leaderboard

Grounded in our INTIMA benchmark, the leaderboard evaluates models across four dimensions of companionship:
🤖 Assistant Traits: the “voice” and role the model projects
🌷 Relationship & Intimacy: whether it signals closeness or bonding
💘 Emotional Investment: the depth of its emotional engagement
🤲 User Vulnerabilities: how it responds to sensitive disclosures

This work builds on our paper with @frimelle and @yjernite .

📢 Now we’d love your perspective: which open models should we test next for the leaderboard? Drop your suggestions in the comments or reach out! Together we can expand the leaderboard and build a clearer picture of what companionship in AI really looks like.

Paper: INTIMA: A Benchmark for Human-AI Companionship Behavior (2508.09998)
INTIMA Benchmark: AI-companionship/INTIMA
  • 1 reply
·