Hugging Face and Lighthouz AI launch the Chatbot Guardrails Arena, a platform to stress-test LLMs and privacy guardrails by having users try to trick chatbots into revealing sensitive financial…
GaLore is a method that reduces memory footprint for training large language models by projecting gradients into low-rank subspaces, enabling training of up to 7 billion parameter models on consumer…
The blog post describes the creation of Cosmopedia, a large-scale synthetic dataset for pre-training LLMs, aiming to replicate the training data used for Phi-1.5.
This blog post explains how to run the Phi-2 small language model locally on a laptop with an Intel Meteor Lake CPU by applying 4-bit quantization using Intel OpenVINO and Optimum Intel, enabling…
Hugging Face introduces Quanto, a PyTorch quantization backend for Optimum, designed for versatility and simplicity, supporting various quantization schemes and devices.
Hugging FaceStory of the weekCapability change· 18 Mar
Hugging Face launches Train on DGX Cloud, a service on the Hugging Face Hub that enables Enterprise Hub organizations to fine-tune open models using NVIDIA H100 GPUs with pay-as-you-go pricing and…
Sakana AI announces Evolutionary Model Merge, a method using evolutionary techniques to combine open-source models, and releases three Japanese foundation models: EvoLLM-JP (LLM), EvoVLM-JP (VLM),…