VE-FORBRYDERNE / mesh-transformer-jax
Fork of kingoflolz/mesh-transformer-jax with memory usage optimizations and support for GPT-Neo, GPT-NeoX, BLOOM, OPT and fairseq dense LM. Primarily used by KoboldAI and mtj-softtuner.
☆22Updated 2 years ago
Alternatives and similar repositories for mesh-transformer-jax
Users that are interested in mesh-transformer-jax are comparing it to the libraries listed below
Sorting:
- Hidden Engrams: Long Term Memory for Transformer Model Inference☆35Updated 3 years ago
- Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance☆28Updated 2 years ago
- One stop shop for all things carp☆59Updated 2 years ago
- 🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.☆56Updated 3 years ago
- Training & Implementation of chatbots leveraging GPT-like architecture with the aitextgen package to enable dynamic conversations.☆49Updated 2 years ago
- Experimental sampler to make LLMs more creative☆31Updated last year
- This project aims to make RWKV Accessible to everyone using a Hugging Face like interface, while keeping it close to the R and D RWKV bra…☆64Updated 2 years ago
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- An open-source replication and extension of the Meta AI's LLAMA dataset☆24Updated 2 years ago
- Merge LLM that are split in to parts☆26Updated last year
- ☆28Updated 2 years ago
- Framework agnostic python runtime for RWKV models☆146Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- A library for squeakily cleaning and filtering language datasets.☆47Updated last year
- rwkv_chatbot☆62Updated 2 years ago
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated 2 years ago
- A client library for LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.☆33Updated 2 years ago
- A basic ui for running gpt neo 2.7B on low vram (3 gb Vram minimum)☆36Updated 3 years ago
- ☆43Updated 2 years ago
- ☆130Updated 2 years ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.☆67Updated 2 years ago
- Local emulator for Hugging Face Inference Endpoints customer handlers☆25Updated last year
- [WIP] A 🔥 interface for running code in the cloud☆85Updated 2 years ago
- Conversational Language model toolkit for training against human preferences.☆42Updated last year
- URL downloader supporting checkpointing and continuous checksumming.☆19Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated 2 years ago
- Smol but mighty language model☆62Updated 2 years ago
- Command-line script for inferencing from models such as LLaMA, in a chat scenario, with LoRA adaptations☆33Updated last year
- ☆40Updated 2 years ago