All tags
Model: "sdxl"
LLMs-as-Juries
gpt-4 gpt-3.5 sdxl ponyxl openai cohere financial-times memory training-data model-usage-limits data-cleansing ai-voice-assistants interface-agents image-generation model-extensions multi-agent-systems
OpenAI has rolled out the memory feature to all ChatGPT Plus users and partnered with the Financial Times to license content for AI training. Discussions on OpenAI's profitability arise due to paid training data licensing and potential GPT-4 usage limit reductions. Users report issues with ChatGPT's data cleansing after the memory update. Tutorials and projects include building AI voice assistants and interface agents powered by LLMs. In Stable Diffusion, users seek realistic SDXL models comparable to PonyXL, and new extensions like Hi-diffusion and Virtuoso Nodes v1.1 enhance ComfyUI with advanced image generation and Photoshop-like features. Cohere finds that multiple agents outperform single agents in LLM judging tasks, highlighting advances in multi-agent systems.
1/3/2024: RIP Coqui
sdxl diffusers-0.25 coqui mozilla hugging-face google text-to-speech performance-optimization token-management transformer-architecture image-datasets web-crawling pytorch leaderboards
Coqui, a prominent open source text-to-speech project from the Mozilla ML group, officially shut down. Discussions in the HuggingFace Discord highlighted skepticism about the claimed
3X faster speed of sdxl, attributing improvements more to techniques like torch.compile and removal of fp16 and attention rather than diffusers 0.25 features. Users confirmed that a HuggingFace user token can be used across multiple machines, though distinct tokens are recommended for safety. The Learning Loss Minimization (LLM) Leaderboard briefly experienced issues but was later confirmed operational. A Kaggle notebook was shared demonstrating how to build Transformer architectures from scratch using PyTorch. Additionally, a new image dataset with 15k shoe, sandal, and boot images was introduced for multiclass classification tasks. Explanations about the workings of the Common Crawl web-crawling process were also shared.