enjalot / latent-saeLinks
Training code for Sparse Autoencoders on Embedding models
☆39Updated 9 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 Sampling☆79Updated last year
- ☆40Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 2 months ago
- NLP with Rust for Python 🦀🐍☆70Updated 7 months ago
- PageRank for LLMs☆51Updated 3 months ago
- ☆25Updated 7 months ago
- ☆55Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 2 months ago
- ☆63Updated last year
- ☆53Updated 10 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- Simple GRPO scripts and configurations.☆59Updated 10 months ago
- ☆90Updated 5 months ago
- ☆29Updated 2 months ago
- Lightweight tools for quick and easy LLM demo's☆28Updated last year
- look how they massacred my boy☆63Updated last year
- Using modal.com to process FineWeb-edu data☆20Updated 8 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last month
- ☆10Updated last year
- Experiments for efforts to train a new and improved t5☆76Updated last year
- ☆50Updated last year
- lossily compress representation vectors using product quantization☆59Updated last month
- Latent Large Language Models☆19Updated last year
- Python library to use Pleias-RAG models☆67Updated 7 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Updated 10 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- PyLate efficient inference engine☆68Updated 3 months ago