FailSpy / abliteratorLinks
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
☆507Updated last year
Alternatives and similar repositories for abliterator
Users that are interested in abliterator are comparing it to the libraries listed below
Sorting:
- ☆316Updated last month
- A benchmark for emotional intelligence in large language models☆359Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆177Updated last year
- A library for making RepE control vectors☆636Updated 8 months ago
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆163Updated last year
- A multimodal, function calling powered LLM webui.☆216Updated 11 months ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆491Updated last year
- Web UI for ExLlamaV2☆513Updated 7 months ago
- function calling-based LLM agents☆287Updated last year
- A fast batching API to serve LLM models☆187Updated last year
- Merge Transformers language models by use of gradient parameters.☆208Updated last year
- A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information☆444Updated last month
- Large-scale LLM inference engine☆1,548Updated last week
- A trivial programmatic Llama 3 jailbreak. Sorry Zuck!☆564Updated 7 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆499Updated this week
- Automatically evaluate your LLMs in Google Colab☆659Updated last year
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆248Updated last year
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆450Updated 11 months ago
- An Open Source Toolkit For LLM Distillation☆726Updated 2 months ago
- Make abliterated models with transformers, easy and fast☆86Updated 5 months ago
- Stop messing around with finicky sampling parameters and just use DRµGS!☆357Updated last year
- ☆161Updated last month
- ☆1,082Updated last year
- Dolphin System Messages☆347Updated 7 months ago
- Visualize the intermediate output of Mistral 7B☆369Updated 7 months ago
- A bagel, with everything.☆324Updated last year
- Fast parallel LLM inference for MLX☆217Updated last year
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆185Updated last year