FailSpy / abliteratorLinks
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
☆551Updated last year
Alternatives and similar repositories for abliterator
Users that are interested in abliterator are comparing it to the libraries listed below
Sorting:
- ☆334Updated 5 months ago
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆165Updated last year
- A benchmark for emotional intelligence in large language models☆396Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information☆453Updated 5 months ago
- A library for making RepE control vectors☆675Updated 3 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- Large-scale LLM inference engine☆1,610Updated last month
- A multimodal, function calling powered LLM webui.☆217Updated last year
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆613Updated this week
- function calling-based LLM agents☆289Updated last year
- Web UI for ExLlamaV2☆514Updated 11 months ago
- This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?☆1,408Updated last month
- The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM …☆610Updated 10 months ago
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆259Updated last year
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆500Updated last year
- ☆135Updated 8 months ago
- Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.☆681Updated 9 months ago
- A fast batching API to serve LLM models☆189Updated last year
- ☆1,166Updated 2 weeks ago
- An Open Source Toolkit For LLM Distillation☆817Updated 2 weeks ago
- Make abliterated models with transformers, easy and fast☆111Updated 3 weeks ago
- A trivial programmatic Llama 3 jailbreak. Sorry Zuck!☆568Updated 11 months ago
- Implements harmful/harmless refusal removal using pure HF Transformers☆1,398Updated last month
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- Stop messing around with finicky sampling parameters and just use DRµGS!☆360Updated last year
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆191Updated last year
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,103Updated 2 weeks ago
- Customizable implementation of the self-instruct paper.☆1,050Updated last year
- Automatically evaluate your LLMs in Google Colab☆678Updated last year