view article Article Hugging Face on AMD Instinct MI455X: First Transformers Results badaoui β’ about 23 hours ago β’ 12
Running 3 Tune it your way: configurable video and depth encoding in LeRobot π₯ 3 A follow-up on video encoding in LeRobot datasets.
view post Post 5319 Gemma 4 is now faster and much more accurate! πGoogle made huge improvements to tool-calling and chat accuracy, reliability + speed.To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4 See translation 8 replies Β· π 30 30 π 14 14 π 6 6 π€ 5 5 π€ 1 1 + Reply
view article Article Native-speed vLLM transformers modeling backend hmellor, lysandre β’ 17 days ago β’ 58
Running Transformers Architecture Inspector π Inspect the semantic architecture IR of Transformers models
Running Featured 463 HF Realtime Voice π 463 Voice chat over WebSocket against a HF speech-to-speech
Running Transformers Architecture Inspector π Inspect the semantic architecture IR of Transformers models