FailSpy / abliteratorLinks
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
☆562Updated 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
- A benchmark for emotional intelligence in large language models☆397Updated last year
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆165Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- A library for making RepE control vectors☆676Updated 4 months ago
- Web UI for ExLlamaV2☆514Updated 11 months ago
- A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information☆455Updated 5 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆622Updated this week
- A multimodal, function calling powered LLM webui.☆217Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- An Open Source Toolkit For LLM Distillation☆833Updated last month
- function calling-based LLM agents☆289Updated last year
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆260Updated last year
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆500Updated last year
- ☆135Updated 8 months ago
- Make abliterated models with transformers, easy and fast☆113Updated last month
- Merge Transformers language models by use of gradient parameters.☆213Updated last year
- A fast batching API to serve LLM models☆188Updated last year
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,115Updated this week
- A trivial programmatic Llama 3 jailbreak. Sorry Zuck!☆567Updated last year
- LLM Frontend in a single html file☆691Updated 3 weeks ago
- The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM …☆612Updated 11 months ago
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆192Updated last year
- Large-scale LLM inference engine☆1,631Updated this week
- Fast parallel LLM inference for MLX☆243Updated last year
- ☆165Updated 5 months ago
- ☆209Updated 3 weeks ago
- Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.☆681Updated 10 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆457Updated last year