facebookresearch / SONAR
SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.
☆717Updated last week
Alternatives and similar repositories for SONAR:
Users that are interested in SONAR are comparing it to the libraries listed below
- Large Concept Models: Language modeling in a sentence representation space☆2,069Updated 2 months ago
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆857Updated last month
- Code for BLT research paper☆1,437Updated last week
- Bringing BERT into modernity via both architecture changes and scaling☆1,297Updated this week
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,449Updated last month
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆300Updated 5 months ago
- ☆502Updated 4 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,336Updated this week
- Training Large Language Model to Reason in a Continuous Latent Space☆998Updated 2 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆277Updated last month
- Pretraining code for a large-scale depth-recurrent language model☆697Updated 2 weeks ago
- Recipes to scale inference-time compute of open models☆1,044Updated last month
- Minimalistic large language model 3D-parallelism training☆1,715Updated this week
- A bibliography and survey of the papers surrounding o1☆1,183Updated 4 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆693Updated 2 weeks ago
- An Open Source Toolkit For LLM Distillation☆554Updated 2 months ago
- Official repository for ORPO☆446Updated 9 months ago
- The repository for the code of the UltraFastBERT paper☆517Updated last year
- ☆1,011Updated 3 months ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,013Updated last month
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆310Updated 3 months ago
- procedural reasoning datasets☆534Updated this week
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,374Updated 11 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆819Updated this week
- Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'☆1,457Updated 2 months ago
- ☆485Updated last week
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆268Updated 3 weeks ago
- Fast State-of-the-Art Static Embeddings☆1,129Updated this week
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆548Updated 3 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,578Updated this week