RT @Tu7uruu: New top ASR model on the Open ASR Leaderboard!. We've just added IBM Granite-Speech-3.3-8b and 2b to the leaderboard! . Open w….

RT @Yikang_Shen: Stick-Breaking Attention: Out-of-box length extrapolation, thanks to removing the position embedding; Better performance t….

RT @ailozovskaya: 🚀 Introducing IBM Granite 3.0 models on the 🤗 Open LLM Leaderboard!. Granite 3.0 is IBM’s newest suite of lightweight, mu….

RT @replicate: We've partnered with IBM to bring the new Granite 3.0 language models to Replicate. These models are trained on license-perm….

RT @danielnewmanUV: I had the chance to dive deep into the new models coming out from IBM with its introduction of Granite 3.0. Upon initi….

RT @ollama: Today, IBM and Ollama announces partnership to bring Granite 3.0 models! 😍. 2 architectures: . Dense: . 2B: .ollama run granite….

Huge thanks to everyone who contributed to this release—it's truly a privilege to work with such amazing colleagues. See the technical report ( for a full list of contributors (too many to list here!). We have a lot more in the pipeline, and I am looking.

You can find the models on Hugging Face (. You can also access them via ollama ( and Replicate (, and of course, via @IBMwatsonx (. The technical report can be found here (will be on.

🎉Today, we're pleased to announce the release of the Granite 3.0 model family, the latest open-licensed, general purpose LLMs from @IBM 🎉. These have been a labor of love for my team at @IBMResearch, working closely with a host of collaborators across the company. We're excited

My daughter hit me yesterday, completely out of the blue, with a detailed and thoroughly researched presentation entitled "Why I should learn to play the harp".

Four fingers, five toes.

RT @Yikang_Shen: Thanks for posting our work! .(1/5) After running thousands of experiments with the WSD learning rate scheduler and μTrans….

tfw I am the sole technical person at a reception full of business people.

RT @PyTorch: Attending the PyTorch Conference? There's several talks and posters on Distributed Training. Folks from IBM, Meta, Databricks….

RT @leokarlin: Thanks for the highlight @_akhaliq!.We offer a simple and nearly-data-free way to move (large quantities) of custom PEFT mod….

RT @Yikang_Shen: Haha, surprise!.

Live leaderboard here: And check out the recently open-sourced Granite Code LLM family here:

and an even bigger lead on SQL efficiency:

More public leaderboard results 🔥. IBM takes first place on the large-scale text-to-SQL BIRD-SQL leaderboard with ExSL + Granite-20b-Code, beating out a host of GPT-4-based solutions. Huge congrats to the global @IBMResearch team that achieved this result.

RT @alibrahimzada: Interested in LLM-based Code Translation 🧐?. Check our CodeLingua leaderboard (. We have updated….