nanoVLM is the simplest way to get started with training your very own Vision Language Model (VLM) using pure PyTorch. It is lightweight toolkit which allows you to launch a VLM training on a free tier colab notebook. We were inspired by Andrej Karpathy’s nanoGPT, and provide a similar project for the vision domain. At its heart, nanoVLM is a toolkit that helps you build and train a model that can understand both images and text, and then generate text […]

Large diffusion models like Flux (a flow-based text-to-image generation model) can create stunning images, but their size can be a hurdle, demanding significant memory and compute resources. Quantization offers a powerful solution, shrinking these models to make them more accessible without drastically compromising performance. But the big question always is: can you actually tell the difference in the final image? Before we dive into the technical details of how various quantization backends in Hugging Face Diffusers work, why not test […]

Check out our official blogpost (EN, AR) We are excited to introduce Falcon-Arabic, a 7B parameter Language Model that sets a new benchmark for Arabic NLP. Built on the Falcon 3 architecture, Falcon-Arabic is a multilingual model that supports Arabic, English, and several other languages. It excels in general knowledge, Arabic grammar, mathematical reasoning, complex problem solving, and understanding the rich diversity of Arabic dialects. Falcon-Arabic supports a context length of 32,000 tokens, allowing it to handle long documents and […]

Introduction Check out also our official blogpost Today, we are proud to introduce the Falcon-H1 series, a collection of six open-source models ranging from 0.5B to 34B parameters, each available in both base and instruction-tuned variants. At the core of these models lies a hybrid architecture that combines the strengths of the classical Transformer-based attention mechanism with the State Space Model (SSM), known    

NEW: tiny-agents now supports AGENTS.md standard. 🥳 Inspired by Tiny Agents in JS, we ported the idea to Python 🐍 and extended the huggingface_hub client SDK to act as a MCP Client so it can pull tools from MCP servers and pass them to the LLM during inference. MCP (Model Context Protocol) is an open protocol that standardizes how Large Language Models (LLMs) interact with external tools and APIs. Essentially, it removed the need to write custom integrations for each […]

This week at Dell Tech World, we announced the new version of Dell Enterprise Hub, with a complete suite of models and applications to easily build AI running on premises with Dell AI servers and AI PCs. Models Ready for Action If you go to the Dell Enterprise Hub today, you can find some of the most popular models, like Meta Llama 4 Maverick,    

Thank you for your great work. Anyway, I tested the liger loss with deepspeed zero3 using Qwen/Qwen2.5-0.5B-Instruct in a bf16.I met an shape mismatch as stated below: [rank0]: Traceback (most recent call last): [rank0]: File “/workspace/temp.py”, line 22, in [rank0]: trainer.train() [rank0]: File “/usr/local/lib/python3.11/dist-packages/transformers/trainer.py”, line 2238, in train [rank0]: return inner_training_loop( [rank0]: ^^^^^^^^^^^^^^^^^^^^ [rank0]: File “/usr/local/lib/python3.11/dist-packages/transformers/trainer.py”, line 2553, in _inner_training_loop [rank0]: tr_loss_step = self.training_step(model, inputs, num_items_in_batch) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File “/usr/local/lib/python3.11/dist-packages/transformers/trainer.py”, line 3730, in training_step [rank0]: loss = self.compute_loss(model, inputs, […]

Today we’re sharing research that bridges two powerful paradigms in AI agent design: the expressiveness of code-based actions and the reliability of structured generation. Our findings show that forcing CodeAgents to generate both thoughts and code in    

TRL supports training LLMs using GRPO, an online learning algorithm recently introduced in the DeepSeekMath paper. In GRPO, the model learns from its own outputs: it generates responses during training, receives feedback, and uses that feedback to improve itself over time. This makes generation a critical step in the training loop — and also a major bottleneck. To speed up generation, TRL integrates with vLLM. This combination lets you train powerful models more efficiently in GRPO setup. However, there’s a […]

Today, we introduce SmolVLA, a compact (450M), open-source Vision-Language-Action model for robotics that runs on consumer hardware. Pretrained only on compatibly licensed, open-source community-shared datasets under the lerobot tag. SmolVLA-450M outperforms much larger VLAs and strong baselines such as ACT on simulation (LIBERO, Meta-World) and real-world tasks (SO100, SO101). Supports asynchronous inference for 30% faster response and 2× task throughput. Useful links: 📚 Table of Contents