harubaru / convogpt
Conversational Language model toolkit for training against human preferences.
☆42Updated 11 months ago
Alternatives and similar repositories for convogpt:
Users that are interested in convogpt are comparing it to the libraries listed below
- A ready-to-deploy container for implementing an easy to use REST API to access Language Models.☆64Updated 2 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☆27Updated 2 years ago
- Image Diffusion block merging technique applied to transformers based Language Models.☆54Updated last year
- Where we keep our notes about model training runs.☆16Updated 2 years ago
- Platform and API Agnostic library for powering chatbots☆24Updated 2 years ago
- Our data munging code.☆34Updated 5 months ago
- Doohickey is a stable diffusion tool for technical artists who want to stay up-to-date with the latest developments in the field.☆39Updated 2 years ago
- ☆27Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated 10 months ago
- k_diffusion wrapper included for k_lms sampling. fixed for notebook.☆20Updated last year
- Instruct-tuning LLaMA on consumer hardware☆66Updated 2 years ago
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bit☆31Updated last year
- Colab notebooks to run a basic AI Dungeon clone using gpt-neo-2.7B☆64Updated 3 years ago
- Hidden Engrams: Long Term Memory for Transformer Model Inference☆35Updated 3 years ago
- Framework agnostic python runtime for RWKV models☆145Updated last year
- ☆28Updated last year
- Inference code for LLaMA models with Gradio Interface and rolling generation like ChatGPT☆48Updated 2 years ago
- rwkv_chatbot☆62Updated 2 years ago
- 📖 — Notebooks related to RWKV☆59Updated last year
- ☆28Updated last year
- 🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.☆56Updated 3 years ago
- BlinkDL's RWKV-v4 running in the browser☆47Updated 2 years ago
- Simple extension for text-generation-webui that injects recent conversation history into the negative prompt with the goal of minimizing …☆33Updated last year
- Cleaning discord data for NLP☆27Updated 3 years ago
- oobabooga extension - Experimental sampler to make LLMs more creative☆23Updated last year
- Updated 3 weeks ago
- Experimental sampler to make LLMs more creative☆30Updated last year
- Fork of kingoflolz/mesh-transformer-jax with memory usage optimizations and support for GPT-Neo, GPT-NeoX, BLOOM, OPT and fairseq dense L…☆22Updated 2 years ago
- Instruct-tune LLaMA on consumer hardware☆73Updated last year
- 8-bit CUDA functions for PyTorch☆44Updated last year