Stars
Open-source State-of-the-art TTS model which runs on a CPU 😻
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
Low-bit LLM inference on CPU/NPU with lookup table
Official inference framework for 1-bit LLMs
</> htmx - high power tools for HTML
Attempt at a functional description of Wormhole vector instructions
Puzzles for learning Triton
Tile primitives for speedy kernels
A native, user-mode, multi-process, graphical debugger.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Running large language models on a single GPU for throughput-oriented scenarios.
rom1504 / CLIP
Forked from openai/CLIPContrastive Language-Image Pretraining
React app implementing OpenAI and Google APIs to re-create behavior of the toolformer paper.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Mixture of Diffusers for scene composition and high resolution image generation
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)