facebookresearch / metaseq
Repo for external large-scale work
☆6,516Updated 9 months ago
Alternatives and similar repositories for metaseq:
Users that are interested in metaseq are comparing it to the libraries listed below
- Fast and memory-efficient exact attention☆15,179Updated last week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,255Updated 3 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,185Updated 7 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,557Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,208Updated this week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,570Updated last year
- Ongoing research training transformer models at scale☆11,192Updated this week
- Train transformer language models with reinforcement learning.☆10,781Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,022Updated 4 months ago
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,744Updated 3 weeks ago
- Instruct-tune LLaMA on consumer hardware☆18,777Updated 6 months ago
- An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries☆7,057Updated last week
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,801Updated 10 months ago
- A collection of libraries to optimise AI model performances☆8,371Updated 6 months ago
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,624Updated last month
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆13,039Updated this week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆29,758Updated 6 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,087Updated this week
- ☆2,725Updated last week
- Training and serving large-scale neural networks with auto parallelization.☆3,095Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆8,942Updated last week
- Transformer related optimization, including BERT, GPT☆5,997Updated 10 months ago
- StableLM: Stability AI Language Models☆15,826Updated 9 months ago
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,678Updated last year
- CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.☆4,982Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,247Updated last year
- Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models☆2,937Updated 6 months ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆11,177Updated last month
- Tensor library for machine learning☆11,631Updated this week
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆20,636Updated 3 weeks ago