enjalot / latent-saeLinks
Training code for Sparse Autoencoders on Embedding models
β38Updated 5 months ago
Alternatives and similar repositories for latent-sae
Users that are interested in latent-sae are comparing it to the libraries listed below
Sorting:
- An introduction to LLM Samplingβ79Updated 7 months ago
- NLP with Rust for Python π¦πβ64Updated 2 months ago
- β23Updated 2 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked promptsβ24Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.β32Updated 5 months ago
- utilities for loading and running text embeddings with onnxβ44Updated 11 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignmentβ60Updated 11 months ago
- β38Updated last year
- β49Updated 5 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).β80Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optunaβ55Updated 5 months ago
- Using modal.com to process FineWeb-edu dataβ20Updated 3 months ago
- β87Updated 6 months ago
- Simple GRPO scripts and configurations.β59Updated 5 months ago
- Experiments for efforts to train a new and improved t5β76Updated last year
- β28Updated last month
- β70Updated 2 weeks ago
- look how they massacred my boyβ63Updated 9 months ago
- PageRank for LLMsβ43Updated 3 months ago
- minimal pytorch implementation of bm25 (with sparse tensors)β104Updated last year
- Official repo for Learning to Reason for Long-Form Story Generationβ68Updated 3 months ago
- Pre-train Static Word Embeddingsβ85Updated 2 months ago
- β63Updated 3 weeks ago
- β69Updated 11 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Modeβ¦β49Updated 3 months ago
- [WIP] Transformer to embed Danbooru labelsetsβ13Updated last year
- Lightweight tools for quick and easy LLM demo'sβ28Updated 10 months ago
- β49Updated last year
- β53Updated 8 months ago
- Functional Benchmarks and the Reasoning Gapβ88Updated 10 months ago