enjalot / latent-saeLinks
Training code for Sparse Autoencoders on Embedding models
☆38Updated 3 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:
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- An introduction to LLM Sampling☆78Updated 5 months ago
- ☆57Updated 2 weeks ago
- ☆38Updated 10 months ago
- ☆43Updated 3 months ago
- NLP with Rust for Python 🦀🐍☆62Updated 2 weeks ago
- Using modal.com to process FineWeb-edu data☆20Updated last month
- look how they massacred my boy☆63Updated 7 months ago
- Approximating the joint distribution of language models via MCTS☆21Updated 7 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 3 months ago
- ☆9Updated 7 months ago
- ☆20Updated 3 weeks ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 3 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- ☆48Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated 2 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆58Updated last month
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- ☆21Updated 6 months ago
- ☆49Updated 6 months ago
- Simple GRPO scripts and configurations.☆58Updated 3 months ago
- Pre-train Static Word Embeddings☆70Updated this week
- ☆33Updated 2 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 6 months ago
- Functional Benchmarks and the Reasoning Gap☆86Updated 8 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆28Updated 2 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆50Updated 6 months ago
- Chat Markup Language conversation library☆55Updated last year
- ☆83Updated 4 months ago
- lossily compress representation vectors using product quantization☆54Updated last month