thesephist / spectreLinks
Sparse autoencoders for Contra text embedding models
☆25Updated last year
Alternatives and similar repositories for spectre
Users that are interested in spectre are comparing it to the libraries listed below
Sorting:
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated last month
- ☆40Updated last year
- ☆45Updated 2 years ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- Approximating the joint distribution of language models via MCTS☆22Updated last year
- look how they massacred my boy☆63Updated last year
- Simplex Random Feature attention, in PyTorch☆75Updated 2 years ago
- Using modal.com to process FineWeb-edu data☆20Updated 7 months ago
- utilities for loading and running text embeddings with onnx☆44Updated 3 months ago
- RL gym for vision language models written from scratch☆131Updated last month
- Cerule - A Tiny Mighty Vision Model☆68Updated 3 weeks ago
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆58Updated last year
- KMD is a collection of conversational exchanges between patients and doctors on various medical topics. It aims to capture the intricaci…☆24Updated 2 years ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆76Updated 9 months ago
- Training Models Daily☆17Updated last year
- Plotting (entropy, varentropy) for small LMs☆99Updated 6 months ago
- papers.day☆91Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated last year
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆159Updated 2 years ago
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.☆30Updated 2 years ago
- alternative way to calculating self attention☆18Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated last month
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated 2 years ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆108Updated 8 months ago
- ☆62Updated last year
- inference code for mixtral-8x7b-32kseqlen☆103Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- ☆21Updated 10 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…☆182Updated 3 weeks ago