PygmalionAI / logbooks
Where we keep our notes about model training runs.
☆16Updated 2 years ago
Alternatives and similar repositories for logbooks:
Users that are interested in logbooks are comparing it to the libraries listed below
- Conversational Language model toolkit for training against human preferences.☆42Updated 11 months ago
- ☆27Updated last year
- 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
- Our data munging code.☆34Updated 5 months ago
- Turns KoboldAI into a crowdsourced distributed cluster☆33Updated last year
- Train Llama Loras Easily☆31Updated last year
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- The official front-end UI.☆40Updated last year
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated last year
- Dynamic parameter modulation for oobabooga's text-generation-webui that adjusts generation parameters to better mirror user affect.☆35Updated last year
- An extension to Oobabooga to add a simple memory function for chat☆24Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated 10 months ago
- A KoboldAI-like memory extension for oobabooga's text-generation-webui☆108Updated 4 months ago
- Experimental sampler to make LLMs more creative☆30Updated last year
- BlinkDL's RWKV-v4 running in the browser☆47Updated 2 years ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆43Updated last year
- Simple extension for text-generation-webui that injects recent conversation history into the negative prompt with the goal of minimizing …☆33Updated last year
- The code we currently use to fine-tune models.☆114Updated 10 months ago
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bit☆31Updated last year
- The official service back-end.☆13Updated last year
- 4 bits quantization of LLMs using GPTQ☆48Updated last year
- Image Diffusion block merging technique applied to transformers based Language Models.☆54Updated last year
- Collection of various text datasets to assist ML researchers in training or fine-tuning their models☆20Updated last year
- Sentencepiece based BPE tokenizer for English and Japanese language text.☆27Updated 11 months ago
- Mistral7B playing DOOM☆28Updated 11 months ago
- Diffusion_TTS extension for booga☆66Updated 8 months ago
- CHAracter State Management - a generative text adventure (engine)☆63Updated 5 months ago
- Text WebUI extension to add clever Notebooks to Chat mode☆139Updated last year
- A combination of Oobabooga's fork and the main cuda branch of GPTQ-for-LLaMa in a package format.☆22Updated last year