facebookresearch / metaseq
Repo for external large-scale work
☆6,519Updated 9 months ago
Alternatives and similar repositories for metaseq:
Users that are interested in metaseq are comparing it to the libraries listed below
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,573Updated last year
- An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries☆7,078Updated last week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,028Updated 5 months ago
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆13,090Updated last week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,255Updated 3 months ago
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,272Updated this week
- Ongoing research training transformer models at scale☆11,269Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,608Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,165Updated this week
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,636Updated 2 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,218Updated 7 months ago
- Transformer related optimization, including BERT, GPT☆6,003Updated 10 months ago
- Training and serving large-scale neural networks with auto parallelization.☆3,097Updated last year
- A collection of libraries to optimise AI model performances☆8,372Updated 6 months ago
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,745Updated this week
- ☆2,734Updated last week
- An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.☆8,266Updated 2 years ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆8,974Updated this week
- A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Auto…☆13,030Updated this week
- Train transformer language models with reinforcement learning.☆11,140Updated this week
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆20,673Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆36,587Updated this week
- Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)☆3,857Updated 7 months ago
- LAVIS - A One-stop Library for Language-Vision Intelligence☆10,204Updated 2 months ago
- Example models using DeepSpeed☆6,255Updated this week
- An open source implementation of CLIP.☆10,921Updated last month
- Fast and memory-efficient exact attention☆15,318Updated this week
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,434Updated last year
- An open-source framework for training large multimodal models.☆3,808Updated 5 months ago
- CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.☆4,995Updated last week