🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🚀 Tower+: our latest model in the Tower family — sets a new standard for open-weight multilingual models! We show how to go beyond sentence-level translation, striking a balance between translation quality and general multilingual capabilities. 1/5 arxiv.org/pdf/2506.17080

We made a Guide on mastering LoRA Hyperparameters, so you can learn to fine-tune LLMs correctly! Learn to: • Train smarter models with fewer hallucinations • Choose optimal: learning rates, epochs, LoRA rank, alpha • Avoid overfitting & underfitting 🔗docs.unsloth.ai/get-started/fi…

FP4 support (NVFP4) in LLM compressor (with vLLM)!

Gemma 3n support in vLLM: github.com/vllm-project/v… Only text version for now. Install vLLM from source to use it.

Excellent article by NVIDIA introducing NVFP4 developer.nvidia.com/blog/introduci…

Got vLLM to work with Gemma 3n (text-only) but I had to compile from source. Doesn’t seem to work with VLLM_USE_PRECOMPILED=1. Also, don’t set VLLM_USE_V1=0. The shared KV is only supported by the V1 engine.

I want a Gemma 3n E70B

💡Beyond math/code, instruction following with verifiable constraints is suitable to be learned with RLVR. But the set of constraints and verifier functions is limited and most models overfit on IFEval. We introduce IFBench to measure model generalization to unseen constraints.

Liquid AI open-sources a new generation of edge LLMs! 🥳 I'm so happy to contribute to the open-source community with this release on Hugging Face! LFM2 is a new architecture that combines best-in-class inference speed and quality into 350M, 700M, and 1.2B models.