FailSpy / abliterator
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
☆324Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for abliterator
- This is our own implementation of 'Layer Selective Rank Reduction'☆231Updated 5 months ago
- ☆223Updated 2 weeks ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated 6 months ago
- A library for making RepE control vectors☆478Updated last month
- Low-Rank adapter extraction for fine-tuned transformers model☆162Updated 6 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆273Updated last month
- A multimodal, function calling powered LLM webui.☆205Updated last month
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆126Updated 5 months ago
- function calling-based LLM agents☆278Updated last month
- A bagel, with everything.☆312Updated 6 months ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆401Updated 2 months ago
- A benchmark for emotional intelligence in large language models☆194Updated 3 months ago
- The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM …☆488Updated 3 months ago
- A fast batching API to serve LLM models☆172Updated 6 months ago
- An Open Source Toolkit For LLM Distillation☆350Updated last month
- ☆705Updated last month
- ☆148Updated 3 months ago
- Fast parallel LLM inference for MLX☆146Updated 4 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆201Updated 5 months ago
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆194Updated 6 months ago
- Automatically evaluate your LLMs in Google Colab☆556Updated 6 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆219Updated last week
- ☆448Updated 7 months ago
- Merge Transformers language models by use of gradient parameters.☆202Updated 3 months ago
- Web UI for ExLlamaV2☆438Updated last month
- ☆116Updated 2 months ago
- autologic is a Python package that implements the SELF-DISCOVER framework proposed in the paper SELF-DISCOVER: Large Language Models Self…☆57Updated 8 months ago
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆242Updated this week
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆105Updated last week
- ☆411Updated last year