thesephist / spectre
Sparse autoencoders for Contra text embedding models
☆25Updated 11 months ago
Alternatives and similar repositories for spectre:
Users that are interested in spectre are comparing it to the libraries listed below
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆31Updated last month
- ☆48Updated last year
- Using modal.com to process FineWeb-edu data☆20Updated last week
- Simplex Random Feature attention, in PyTorch☆74Updated last year
- ☆22Updated last year
- A synthetic story narration dataset to study small audio LMs.☆32Updated last year
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆59Updated 11 months ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆153Updated last year
- utilities for loading and running text embeddings with onnx☆44Updated 8 months ago
- look how they massacred my boy☆63Updated 5 months ago
- alternative way to calculating self attention☆18Updated 10 months ago
- Stream of my favorite papers and links☆41Updated 3 weeks ago
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.☆30Updated last year
- ☆20Updated 5 months ago
- ☆38Updated 8 months ago
- ☆60Updated last year
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- ☆26Updated 4 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆50Updated 5 months ago
- Tools to make language models a bit easier to use☆41Updated last week
- KMD is a collection of conversational exchanges between patients and doctors on various medical topics. It aims to capture the intricaci…☆24Updated last year
- A miniature version of Modal☆20Updated 10 months ago
- Cerule - A Tiny Mighty Vision Model☆67Updated 7 months ago
- Lego for GRPO☆26Updated last week
- [Added T5 support to TRLX] A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆47Updated 2 years ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆39Updated 2 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆95Updated last month
- my collection of scripts☆21Updated this week