Sumandora / remove-refusals-with-transformers
Implements harmful/harmless refusal removal using pure HF Transformers
☆172Updated 7 months ago
Alternatives and similar repositories for remove-refusals-with-transformers:
Users that are interested in remove-refusals-with-transformers are comparing it to the libraries listed below
- Make abliterated models with transformers, easy and fast☆38Updated this week
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆391Updated 7 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆102Updated 9 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆167Updated 8 months ago
- ☆253Updated this week
- A multimodal, function calling powered LLM webui.☆213Updated 4 months ago
- Experimental LLM Inference UX to aid in creative writing☆111Updated last month
- automatically quant GGUF models☆151Updated this week
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆141Updated 8 months ago
- ☆151Updated 6 months ago
- A fast batching API to serve LLM models☆180Updated 9 months ago
- An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.☆220Updated last month
- Web UI for ExLlamaV2☆470Updated this week
- Evaling and unaligning Chinese LLM censorship☆46Updated 4 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆120Updated this week
- idea: https://github.com/nyxkrage/ebook-groupchat/☆85Updated 5 months ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated 9 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆232Updated 8 months ago
- LLM Frontend in a single html file☆313Updated 2 weeks ago
- Easily view and modify JSON datasets for large language models☆69Updated 3 months ago
- ☆78Updated last week
- ☆182Updated this week
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆67Updated 4 months ago
- A frontend for creative writing with LLMs☆115Updated 6 months ago
- A pipeline parallel training script for LLMs.☆121Updated this week
- SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.☆246Updated this week
- An OAI compatible exllamav2 API that's both lightweight and fast☆751Updated 2 weeks ago
- Formatron empowers everyone to control the format of language models' output with minimal overhead.☆177Updated 3 weeks ago
- transparent proxy server for llama.cpp's server to provide automatic model swapping☆152Updated last week
- Open source LLM UI, compatible with all local LLM providers.☆170Updated 4 months ago