Gryphe / MergeMonster
An unsupervised model merging algorithm for Transformers-based language models.
☆106Updated 10 months ago
Alternatives and similar repositories for MergeMonster:
Users that are interested in MergeMonster are comparing it to the libraries listed below
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 10 months ago
- ☆27Updated last year
- Let's create synthetic textbooks together :)☆73Updated last year
- ☆111Updated 3 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- Image Diffusion block merging technique applied to transformers based Language Models.☆54Updated last year
- Genertaes control vectors for use with llama.cpp in GGUF format.☆18Updated 6 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆233Updated 9 months ago
- Easily view and modify JSON datasets for large language models☆71Updated 2 weeks ago
- idea: https://github.com/nyxkrage/ebook-groupchat/☆86Updated 7 months ago
- Merge Transformers language models by use of gradient parameters.☆205Updated 7 months ago
- A pipeline parallel training script for LLMs.☆129Updated last week
- GPT-2 small trained on phi-like data☆65Updated last year
- 5X faster 60% less memory QLoRA finetuning☆21Updated 9 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 11 months ago
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated last year
- An Extension for oobabooga/text-generation-webui☆36Updated last year
- ☆152Updated 8 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆52Updated last week
- ☆65Updated 9 months ago
- ☆113Updated 5 months ago
- After my server ui improvements were successfully merged, consider this repo a playground for experimenting, tinkering and hacking around…☆56Updated 7 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆117Updated last year
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year
- Experimental sampler to make LLMs more creative☆30Updated last year
- A benchmark for role-playing language models☆88Updated this week
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆137Updated last month
- Full finetuning of large language models without large memory requirements☆93Updated last year