chansung
@algo_diver
Followers
5K
Following
13K
Media
426
Statuses
5K
@GoogleDevExpert for ML and @googlecloud | @huggingface Fellow | @dstackai Ambassador | @MistralAI Ambassador | Researcher | Engineering | Open Source Lover
Daejeon, Republic of Korea
Joined August 2018
RT @QGallouedec: Merry Christmas 🎁 GSPO is in TRL. Looking forward to see your reward curves 📈
0
17
0
RT @satyanadella: Today we’re releasing GitHub Spark — a new tool in Copilot that turns your ideas into full-stack apps, entirely in natura….
0
3K
0
RT @GoogleLabs: We just discovered the 🔥 COOLEST 🔥 trick in Flow that we have to share:. Instead of wordsmithing the perfect prompt, you ca….
0
381
0
RT @Hesamation: the legendary @danielhanchen just made a full 3-hour workshop on reinforcement learning and agents. he goes through RL fu….
0
180
0
RT @casper_hansen_: vLLM is finally addressing a long-standing problem: startup times. 35s -> 2s for CUDA graph capture is a great reductio….
0
43
0
RT @mervenoyann: Now it's possible to do RAG with any-to-any models 🔥. Learn how to search in a video dataset and generate using OmniEmbed,….
0
52
0
RT @sophiamyang: How to train a model that actually understands both audio and text like Voxtral from @MistralAI? Here is a quick video wal….
0
136
0
RT @Wauplin: Big update: Hugging Face Inference Providers now work out of the box with the OpenAI client!. Just add the provider name to th….
0
7
0
RT @liliang_ren: We’re open-sourcing the pre-training code for Phi4-mini-Flash, our SoTA hybrid model that delivers 10× faster reasoning th….
github.com
Simple & Scalable Pretraining for Neural Architecture Research - microsoft/ArchScale
0
215
0
RT @SergioPaniego: Repo: We're also open to new ideas from the community 🤗!.
github.com
Inference, Fine Tuning and many more recipes with Gemma family of models - huggingface/huggingface-gemma-recipes
0
2
0
RT @sophiamyang: Super excited to announce the latest features in @MistralAI le Chat:. 🔍 Deep Research: dive into complex topics with our s….
0
79
0
RT @OfficialLoganK: Veo 3 is now live in the Gemini API 📽️!! . Veo 3 is state of the art, can natively generative audio in the videos, come….
0
71
0
RT @NeurIPSConf: NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year,….
0
113
0
RT @deedydas: Google DeepMind just dropped this new LLM model architecture called Mixture-of-Recursions. It gets 2x inference speed, reduc….
0
452
0
RT @danielhanchen: Highly recommend this Stanford lecture video with @_jasonwei and @hwchung27 :).It's one of my favorites on scaling laws….
0
62
0
RT @Teknium1: In case the post was too vague, yes - this is the Hermes 3 dataset. - 1 Million Samples.- Created SOTA without the censorship….
0
55
0
RT @MistralAI: Read our blog for more details:
mistral.ai
Introducing frontier open source speech understanding models.
0
13
0
RT @EnricoShippole: We open-sourced 99% of US caselaw on @huggingface. Both AI and legal tech companies are selling this data for a high pr….
huggingface.co
0
406
0
RT @m4rkmc: 📣 Gemini CLI roadmap. It has been so cool seeing everyone building with the Gemini CLI (60k ⭐s!), and sharing feedback (1k open….
0
22
0