ztjhz
Follow
Stars
Gemma open-weight LLM library, from Google DeepMind
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
real time face swap and one-click video deepfake with only a single image
ASL to text caption for sign language Tik Tok Creaters
by ex-googlers, for ex-googlers - a lookup table of similar tech & services
A set of Python scripts that makes your experience on TPU better
AndroidWorld is an environment and benchmark for autonomous agents
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
llama3 implementation one matrix multiplication at a time
A JAX research toolkit for building, editing, and visualizing neural networks.
Source code for Ayaka's smart home AI assistant
Rich is a Python library for rich text and beautiful formatting in the terminal.
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Einsum-like high-level array sharding API for JAX
JAX implementation of the Mistral 7b v0.2 model
a state-of-the-art-level open visual language model | 多模态预训练模型
Links to conference/journal publications in automated fact-checking (resources for the TACL22/EMNLP23 paper).
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
Codebase for Merging Language Models (ICML 2024)
【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection