ksadov / FREUDLinks
Visualization and sparse autoencoder training for mechanistic interpretability on audio models
☆23Updated 10 months ago
Alternatives and similar repositories for FREUD
Users that are interested in FREUD are comparing it to the libraries listed below
Sorting:
- An introduction to LLM Sampling☆79Updated last year
- ☆30Updated 9 months ago
- A simple, hackable text-to-speech system in PyTorch and MLX☆187Updated 6 months ago
- Speaker Diarization with Transformers☆70Updated 8 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- Video+code lecture on building nanoGPT from scratch☆68Updated last year
- python bindings for symphonia/opus - read various audio formats from python and write opus files☆77Updated last month
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆110Updated 11 months ago
- Collection of Open Source Speech Data☆164Updated 4 months ago
- Joint speech-language model - respond directly to audio!☆30Updated last year
- ☆162Updated last year
- ☆90Updated 7 months ago
- I publish my weekly research here☆20Updated 7 months ago
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆155Updated 6 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆85Updated 5 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 9 months ago
- Training code for Sparse Autoencoders on Embedding models☆39Updated 11 months ago
- A HuggingFace compatible Small Language Model trainer.☆76Updated last year
- ☆157Updated 2 years ago
- Datamodels for hugging face tokenizers☆87Updated this week
- smol models are fun too☆93Updated last year
- code for training & evaluating Contextual Document Embedding models☆202Updated 8 months ago
- High-Performance Engine for Multi-Vector Search☆207Updated 3 weeks ago
- ☆323Updated last year
- SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on On…☆228Updated 8 months ago
- lossily compress representation vectors using product quantization☆59Updated 3 months ago
- ☆141Updated 5 months ago
- run embeddings in MLX☆97Updated last year
- ☆68Updated last year
- Cerule - A Tiny Mighty Vision Model☆68Updated 3 months ago