EGjoni / DRUGS
Stop messing around with finicky sampling parameters and just use DRµGS!
☆347Updated 10 months ago
Alternatives and similar repositories for DRUGS:
Users that are interested in DRUGS are comparing it to the libraries listed below
- A library for making RepE control vectors☆562Updated 2 months ago
- ☆276Updated 2 months ago
- Visualize the intermediate output of Mistral 7B☆348Updated 2 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆605Updated last week
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 11 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆169Updated this week
- An implementation of bucketMul LLM inference☆216Updated 9 months ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆224Updated 11 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆233Updated 10 months ago
- Mistral7B playing DOOM☆130Updated 8 months ago
- a curated list of data for reasoning ai☆133Updated 7 months ago
- Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.☆380Updated last year
- Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) wor…☆210Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Y'all thought the dead internet theory wasn't real, but HERE IT IS☆180Updated 11 months ago
- Merge Transformers language models by use of gradient parameters.☆205Updated 7 months ago
- Experimental BitNet Implementation☆61Updated last year
- Erasing concepts from neural representations with provable guarantees☆226Updated 2 months ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆203Updated 4 months ago
- A multimodal, function calling powered LLM webui.☆214Updated 6 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆230Updated last month
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆342Updated 8 months ago
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆112Updated last year
- ☆152Updated 8 months ago
- Dead Simple LLM Abliteration☆211Updated last month
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆138Updated last month
- The repository for the code of the UltraFastBERT paper☆516Updated last year
- ☆253Updated last year
- WebGPU LLM inference tuned by hand☆149Updated last year