Amazing work!! Prince Canuma 🚀

Very nice work! Dhia eddine Rhaiem More options now for Falcon-H1 full fine-tuning and LoRA tuning with LLaMA-Factory LLaMA Factory

We just released the fine-tuning code and fine-tuned models of BitVLA in Huggingface🔥🔥 Enjoy these hyper-efficient 1-bit VLA models! Code: github.com/ustcwhy/BitVLA Models: huggingface.co/collections/ho…

We’re organizing the E2LM competition at #NeurIPS2025, focused on early-stage training evaluations of Large Language Models. Registration is now open — join us and help revolutionize how we evaluate LLMs! 🚀

🚀 Exciting news! Falcon-H1 & Falcon-E are now on Oumi — the open-source platform for training, fine-tuning (SFT, LoRA, QLoRA), and deploying LLMs anywhere: laptops, cloud, or clusters. Start building: github.com/oumi-ai/oumi/t… #FalconH1 #FalconE #OpenSourceAI #LLM

Latest mlx-lm is out! pip install -U mlx-lm Bunch of new models: - SmolLM3 (Hugging Face) - Ernie family (Baidu) - BitNet (Microsoft) - Falcon-E (TII) - Text-only Gemma3n (Google) - MiniCPM4 (OpenBMB) - AFM (Apple) +Performance improvements for DWQ, dynamic quantization, and

Excited to have contributed into Falcon-E (Bitnet) integration with Prince Canuma Awni Hannun in mlx-lm Falcon-E now fully supported in mlx-lm - as simple as `mlx_lm.generate --model tiiuae/Falcon-E-1B-Instruct --prompt "Implement bubble sort" --max-tokens 100 --temp 0.1` 🚀

Falcon-H1 now runs natively on your device via llama.cpp—0.5B to 34B models, no server needed. Fast inference, long context, multilingual, tool-ready. Build, test, and go beyond. #FalconH1 #LocalLLM #AIOnDevice #EdgeAI #OpenSourceAI

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance Falcon's side-by-side attention-SSM hybrid model. Very detailed, from tokenizers to data preparation and optimization strategies.

Falcon-H1 A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

Falcon-H1 is a very dense research paper exploring the space of hybrid attention designs and tuning *every* hyperparameter there is. It's more interesting than models themselves. If you were intrigued by that «AlphaGo move» slop, this is the real thing.

Great updates!

It’s concerning how recent model releases flex on a handful of benchmarks - but miss the bigger picture: world knowledge, nuance, common sense. Are we still building foundation models, or just performance models? VIBE CHECK: that’s all you need.

🎉 Excited to share: We’ve open-sourced Triton-distributed MegaKernel! A fresh, powerful take on MegaKernel for LLMs—built entirely on our Triton-distributed framework. github.com/ByteDance-Seed… Why it’s awesome? 🧩 Super programmable ⚡ Blazing performance 📊 Rock-solid precision

Omar Sanseviero Congrats on the release, but you forgot to include the SoTA in the chart: Falcon-H1-0.5B Technology Innovation Institute huggingface.co/tiiuae/Falcon-…

🚀 Amazing community project! vLLM CLI — a command-line tool for serving LLMs with vLLM: ✅ Interactive menu-driven UI & scripting-friendly CLI ✅ Local + HuggingFace Hub model management ✅ Config profiles for perf/memory tuning ✅ Real-time server & GPU monitoring ✅ Error

📢 New paper from Ai2: Signal & Noise asks a simple question—can language model benchmarks detect a true difference in model performance? 🧵