FailSpy / abliteratorLinks
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
☆530Updated last year
Alternatives and similar repositories for abliterator
Users that are interested in abliterator are comparing it to the libraries listed below
Sorting:
- A benchmark for emotional intelligence in large language models☆382Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆239Updated last year
- ☆326Updated 3 months ago
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆165Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆179Updated last year
- A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information☆452Updated 3 months ago
- function calling-based LLM agents☆289Updated last year
- A multimodal, function calling powered LLM webui.☆217Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆221Updated last year
- Merge Transformers language models by use of gradient parameters.☆208Updated last year
- Web UI for ExLlamaV2☆514Updated 9 months ago
- A library for making RepE control vectors☆662Updated last month
- A trivial programmatic Llama 3 jailbreak. Sorry Zuck!☆565Updated 9 months ago
- Fast parallel LLM inference for MLX☆232Updated last year
- Large-scale LLM inference engine☆1,591Updated last week
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆495Updated last year
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆254Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆108Updated last year
- A bagel, with everything.☆324Updated last year
- ☆163Updated 3 months ago
- A community list of common phrases generated by GPT and Claude models☆79Updated 2 years ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆450Updated last year
- A fast batching API to serve LLM models☆188Updated last year
- Dolphin System Messages☆363Updated 9 months ago
- Make abliterated models with transformers, easy and fast☆92Updated 7 months ago
- 1.58-bit LLaMa model☆83Updated last year
- Automatically evaluate your LLMs in Google Colab☆670Updated last year
- automatically quant GGUF models☆214Updated 3 weeks ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆571Updated last week
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆190Updated last year