PygmalionAI / logbooks
Where we keep our notes about model training runs.
☆16Updated last year
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.☆41Updated 10 months ago
- Collection of various text datasets to assist ML researchers in training or fine-tuning their models☆20Updated last year
- ☆27Updated last year
- The official front-end UI.☆40Updated last year
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bit☆31Updated last year
- Tools with GUI for GPT finetune data preparation☆23Updated 3 years ago
- BlinkDL's RWKV-v4 running in the browser☆47Updated last year
- ChatGPT-like Web UI for RWKVstic☆100Updated last year
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated last year
- Under construction. API documentation and clients for CharHub.☆38Updated 7 months ago
- Our data munging code.☆34Updated 4 months ago
- The code we currently use to fine-tune models.☆113Updated 9 months ago
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- A discord bot that roleplays!☆147Updated last year
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆111Updated last year
- C/C++ implementation of PygmalionAI/pygmalion-6b☆55Updated last year
- A KoboldAI-like memory extension for oobabooga's text-generation-webui☆107Updated 3 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- A Qt GUI for large language models☆41Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆104Updated 9 months ago
- Turns KoboldAI into a crowdsourced distributed cluster☆33Updated last year
- 4 bits quantization of LLMs using GPTQ☆47Updated last year
- A simple batch file to make the oobabooga one click installer compatible with llama 4bit models and able to run on cuda☆21Updated last year
- Dynamic parameter modulation for oobabooga's text-generation-webui that adjusts generation parameters to better mirror user affect.☆34Updated 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 last year
- Train Llama Loras Easily☆30Updated last year
- Text WebUI extension to add clever Notebooks to Chat mode☆139Updated last year
- Experimental sampler to make LLMs more creative☆30Updated 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
- Discord bot that uses KoboldAI. Supports tavern cards and json files.☆64Updated last year