
frontend engineer @huggingface 🤗 owner of https://teapawt.net/t.co/qUkTYAiUep and https://teapawt.net/t.co/LAhgXUiUuc
qc
Joined August 2022
- Tweets163
- Following39
- Followers570
- Likes501
enzo retweeted
OpenRouter Broadcast sends every trace wherever you want. Now that includes Hugging Face Buckets 🪣
With one setting in @OpenRouter and you can send them to a bucket you own with zero code changes.
→ fine-tune or distill on your own agent runs
→ run online evals on real traffic
→ find which calls burn your budget
Setup: openrouter.ai/docs/guides/fe…
enzo retweeted
ok I had to try: same demo, open model.
DiffusionGemma 26B-A4B + vLLM PR #57250 (structured reads) on my own custom endpoint. Using Matt's exact same sentences 👀
Mostly the same answers, a few fun misses (it thinks Luigi is blue 😂)
Les étudiants ici, je sais que pour bcp c'est compliqué financièrement d’acheter toutes les fournitures, mettez en réponse les liens de ce dont vous avez besoin je vais essayer de trouver une marque avec qui faire une opé et jvous reverserai l'intégralité en fournitures scolaires
enzo retweeted
LTX-2 trainer is a huge deal. I tried it to add water to the podracers scene using their demo water-sim fine-tune (it's a fine-tune whose only goal is to add water :D)
I think we're going to see film productions that don't use general models. They'll train their own fine-tunes, built for exactly what they need and consistent between shots for long content.
enzo retweeted
GLM-5.2 is available on Hugging Face 🔥
It's an important day for open source AI: opus-class frontier intelligence, 1M context, agentic-first by design.
--> The future of AI and humanity is open
Introducing GLM-5.2: Frontier Intelligence, Open Weights
- Significant improvements in coding and agentic tasks
- Strong long-horizon capabilities with a 1M context window
- Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency
- MIT-licensed open weights
- Same API pricing as GLM-5.1
Tech Blog: z.ai/blog/glm-5.2
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.2
Coding Plan: z.ai/subscribe
Chat: chat.z.ai
enzo retweeted
Created gaussian splats website for famous Paris monuments. Connected my claude code to HF Spaces API that let it call gaussian splatting tool (TripoSplat by VAST AI). I will explain 🧵
enzo retweeted
🐳 is back!
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.
🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.
Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today!
📄 Tech Report: huggingface.co/deepseek-ai/D…
🤗 Open Weights: huggingface.co/collections/d…
1/n
enzo retweeted
je testais le service messagerie.numerique.gouv.fr, je vois que la création d'alias ne marche pas, et je trouve ça dans les logs
merci pour tout les devs
enzo retweeted
you can use gmod to verify your age by the way
Discord announces that users will need to verify their age from early March onwards in-order-to access age restricted content.
All accounts will be set to a “teen-by-default” experience until otherwise verified as an adult.
(discord.com/press-releases/d…)
enzo retweeted
New on HF Hub: you can now see check your hardware compatibility with MLX models directly on the model pages 🥳
enzo retweeted
GradientGen, my open-source and 100% free gradient creation tool, is now available!
I'm excited to see what you'll do with it, have fun! :)
GradientGen V1 is out!
- 8 gradient modes
- 20+ variables
- Export up to 8000 pixels
- Unlimited use
Enjoy ! noegarsoux.github.io/Gradien…🔷
enzo retweeted
🤗 @huggingface's most impactful contributors you should follow for the month of October is out! 🚀🚀 huggingface.co/spaces/TCTF/T…
🏛️ Top 10 Model likes: @TheBlokeAI, #mradermacher, @bartowski1182, #lllyasviel, #hexgrad, #nitrosocke, @kijaidesign, @haruu1367, @prompthero, #WarriorMama777
📊 Top 10 Dataset likes: @fkadev, @teknium, @maximelabonne, #gsdf, #Nerfgun3, @imhaotian, @OilandLuca, @logcong0120, @jon_durbin, #anon8231489123
🚀 Top 10 Space likes: @fffiloni, @multimodalart, @enzostvs, @flngr, @_akhaliq, @kingnish24, @xenovacom, @angrypenguinpng, @gokayfem, @yvrjsharma
🤗 Top 10 Profile followers: @TheBlokeAI, @lvminzhang, @mervenoyann, @bartowski1182, @_akhaliq, @ylecun, @fffiloni, @xenovacom, @maximelabonne, @Teknium
Congarts to all users 🔥🔥
enzo retweeted
New: Qwen-Image-2509-MultipleAngles. Very solid model and probably a lot of creative use cases to find with it.
⬇️ Free demo available on Hugging Face
enzo retweeted
The main breakthrough of GPT-5 was to route your messages between a couple of different models to give you the best, cheapest & fastest answer possible.
This is cool but imagine if you could do this not only for a couple of models but hundreds of them, big and small, fast and slow, in any language or specialized for any task - all at inference time. This is what we're introducing with HuggingChat Omni, powered by over 100 open-source models including gpt-oss, deepseek, qwen, kimi, smolLM, gemma, aya and many more already!
And this is just the beginning as there are over 2 millions open models not only for text but image, audio, video, biology, chemistry, time-series and more on @huggingface!
enzo retweeted
Introducing: HuggingChat Omni 💫
Select the best model for every prompt automatically 🚀
- Automatic model selection for your queries
- 115 models available across 15 providers
Available now all Hugging Face users. 100% open source.

































