digitous Goto Github PK

easy-llm-peft-gui

Fuses Language Model Adapters [LoRA, QLoRA, etc] to any chosen base model with three popups for model, peft, save location.

enhanced-lm-mixer

This is a modified language model weight-sum merge script based off of LostRuin's work. Enhancements include migrating copies of necessary files to run the model to the new model folder as well as enhanced console output.

gptq-for-gpt-neox

4 bits quantization of LLaMa using GPTQ [Project to add GPT-NeoX and Pythia quant and inference]

koboldai

llm-slerp-merge

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

lm_transformers_blockmerge

Image Diffusion block merging technique applied to transformers based Language Models.

modelrevolver

Model REVOLVER, a human in the loop model mixing system.

stratusscope

LayerScope is a language model tool that loads two language models of the same architecture and parameter size and generates a bar graph detailing which layers have the most difference between the models.