enjalot / latent-sae
Training code for Sparse Autoencoders on Embedding models
☆38Updated 2 months ago
Alternatives and similar repositories for latent-sae:
Users that are interested in latent-sae are comparing it to the libraries listed below
- ☆38Updated 9 months ago
- NLP with Rust for Python 🦀🐍☆62Updated 11 months ago
- Lightweight tools for quick and easy LLM demo's☆26Updated 7 months ago
- ☆48Updated last year
- ☆48Updated 6 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆39Updated 3 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Using modal.com to process FineWeb-edu data☆20Updated last month
- ☆20Updated 6 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated last month
- An introduction to LLM Sampling☆77Updated 4 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 2 months ago
- ☆35Updated 2 weeks ago
- look how they massacred my boy☆63Updated 6 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated 2 weeks ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 8 months ago
- ☆54Updated this week
- Latent Large Language Models☆18Updated 8 months ago
- utilities for loading and running text embeddings with onnx☆44Updated 8 months ago
- ☆21Updated 6 months ago
- ☆28Updated 7 months ago
- Simple GRPO scripts and configurations.☆58Updated 3 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆27Updated last month
- Binary vector search example using Unum's USearch engine and pre-computed Wikipedia embeddings from Co:here and MixedBread☆18Updated last year
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆23Updated 3 weeks ago
- Chat Markup Language conversation library☆55Updated last year
- ☆21Updated 5 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆46Updated 3 weeks ago
- ☆9Updated 6 months ago