Open Source
Latest AI signals in this category
Open Sourceother
New Vulkan Functions Added in Llama.cpp Release
The latest release of Llama.cpp introduces new Vulkan functions for tensor manipulation and updates across multiple platforms.
llama.cpp Releases
Open Sourceimage
vLLM Releases v0.18.2rc0 Update
The v0.18.2rc0 release includes a fix for handling the max_pixels parameter in the PaddleOCR-VL image processor across transformations.
vLLM Releases
Open Sourceother
New Release of llama.cpp Supports Multiple Platforms
The latest release of llama.cpp includes support for various operating systems and architectures, including macOS, Linux, Android, and Windows. This update enhances compatibility for developers working across different environments.
llama.cpp Releases
Open Sourceother
New Release of llama.cpp Supports Multiple Platforms
The latest release of llama.cpp includes support for various operating systems and architectures, including macOS, Linux, Android, and Windows. It also features a specification update to discard the last drafted token with low probability.
llama.cpp Releases
Open Sourceother
Llama.cpp Updates Hexagon Configuration Options
The latest release of Llama.cpp introduces configurable virtual memory and buffer sizes for Hexagon, along with various enhancements and support for multiple platforms including macOS, Linux, Android, and Windows.
llama.cpp Releases
Open Sourceother
Llama.cpp Updates Vocab Compatibility Checks
The latest release of Llama.cpp includes fixes for vocabulary compatibility checks in the spec example and updates to logging for draft and target model vocabulary mismatches. It supports multiple platforms including macOS, Linux, Android, and Windows.
llama.cpp Releases
© Together AI BlogOpen Sourceother
Aurora: Open-source RL Framework for Speculative Decoding
Aurora is an open-source reinforcement learning framework that enhances speculative decoding by allowing it to learn from each request it serves, rather than relying on a static setup.
Together AI Blog
© Google Research BlogOpen Sourceresearch
WAXAL: Open Resource for African Language Speech Tech
Google Research has introduced WAXAL, a large-scale open resource aimed at advancing speech technology for African languages. This initiative seeks to enhance natural language processing capabilities in underrepresented languages.
Google Research Blog
© Together AI BlogOpen Sourcecoding
CoderForge-Preview: New Open Dataset Released
Together AI has announced the release of CoderForge-Preview, a state-of-the-art open dataset designed for training efficient coding agents.
Together AI Blog
© Together AI BlogOpen Sourceother
Choosing the Right Open Model for Production
The article provides guidance on selecting open-source models for production by assessing model quality, performance benchmarks, and deployment considerations regarding cost, speed, and accuracy.
Together AI Blog
© Replicate BlogOpen Sourcevideo
Open source video model Wan 2.2 released
Replicate has announced Wan 2.2, their fastest and cheapest open source video model to date.
Replicate Blog
Open Sourceother
The Frontier is Open
Together AI has announced the opening of their new platform, allowing developers to access and utilize their AI tools more freely.
Together AI Blog
© EleutherAI BlogOpen Sourceresearch
Common Pile v0.1 Dataset Released
EleutherAI has announced the release of Common Pile v0.1, an 8TB dataset consisting of public domain and openly licensed text.
EleutherAI Blog
© Replicate BlogOpen Sourcevideo
Fine-tune open-source video models now available
Users can now train their own versions of Tencent's HunyuanVideo for style, motion, and character customization on the Replicate platform.
Replicate Blog
© Replicate BlogOpen Sourcemodels
FLUX fine-tunes optimization announced
Replicate has improved the speed of running fine-tunes for FLUX, and these optimizations are available as open-source.
Replicate Blog
© Replicate BlogOpen Sourceother
FLUX Optimizations Released as Open Source
FLUX has been optimized for speed on Replicate, and these improvements have been made available as open-source for further development.
Replicate Blog
© Replicate BlogOpen Sourceimage
New Open Source Image Model and Tools Released
Replicate has announced an open source frontier image model that allows users to cut objects from videos, along with a new Python web framework developed by Jeremy Howard.
Replicate Blog
© EleutherAI BlogOpen Sourceother
Open Source Pipeline for Auto-Interpretability Released
EleutherAI has announced the development of an open-source pipeline aimed at enhancing the interpretability of sparse autoencoder features.
EleutherAI Blog
© Replicate BlogOpen Sourceimage
Run Stable Diffusion 3 Locally with ComfyUI
Users can now run Stable Diffusion 3 on their own machines using ComfyUI by executing a few terminal commands. This allows for local experimentation with the model on GPU-powered systems.
Replicate Blog
© Replicate BlogOpen Sourceother
Replicate Intelligence #1 Overview
The Replicate Blog discusses a DIY implementation of Llama 3, introduces open-source smart glasses, and explores steering language models using dictionary learning techniques.
Replicate Blog
© Replicate BlogOpen Sourcemusic
Voice Cloning with Open-Source Models
Replicate has introduced fine-tuning for realistic voice cloning (RVC), allowing users to train models on their own datasets from YouTube videos using a simple code interface.
Replicate Blog
© EleutherAI BlogOpen Sourceother
Minetester: Open RL Environment on Minetest
Minetester is introduced as a fully open reinforcement learning environment built on the Minetest platform, along with an overview of its preliminary work.
EleutherAI Blog
© EleutherAI BlogOpen Sourceother
EleutherAI Yearly Retrospective Released
EleutherAI has published a detailed retrospective covering their activities over the past year.
EleutherAI Blog
© EleutherAI BlogOpen Sourceother
Open Source Large Language Model for AI Safety
EleutherAI discusses the benefits of releasing a large language model as a means to enhance AI safety. The blog outlines their reasoning behind this belief.
EleutherAI Blog
