Sumandora / remove-refusals-with-transformers
Implements harmful/harmless refusal removal using pure HF Transformers
☆629Updated 9 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
- Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens☆426Updated 9 months ago
- Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)☆539Updated this week
- An OAI compatible exllamav2 API that's both lightweight and fast☆846Updated this week
- Make abliterated models with transformers, easy and fast☆59Updated last week
- Evaling and unaligning Chinese LLM censorship☆58Updated 5 months ago
- transparent proxy server for llama.cpp's server to provide automatic model swapping☆421Updated this week
- LM inference server implementation based on *.cpp.☆131Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆202Updated this week
- This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?☆965Updated last month
- Convert Compute And Books Into Instruct-Tuning Datasets! Makes: QA, RP, Classifiers.☆1,355Updated 3 weeks ago
- Large-scale LLM inference engine☆1,325Updated this week
- ☆2,331Updated last week
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆146Updated 9 months ago
- Review/Check GGUF files and estimate the memory usage and maximum tokens per second.☆127Updated last week
- multi1: create o1-like reasoning chains with multiple AI providers (and locally). Supports LiteLLM as backend too for 100+ providers at o…☆345Updated last month
- A multimodal, function calling powered LLM webui.☆215Updated 5 months ago
- Dolphin System Messages☆272Updated 3 weeks ago
- automatically quant GGUF models☆160Updated this week
- ☆826Updated 6 months ago
- Web UI for ExLlamaV2☆485Updated last month
- ☆270Updated last month
- Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLa…☆353Updated this week
- What If Language Models Expertly Routed All Inference? WilmerAI allows prompts to be routed to specialized workflows based on the domain …☆600Updated this week
- The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM …☆538Updated 3 weeks ago