facebookresearch / mexmaLinks
MEXMA: Token-level objectives improve sentence representations
☆42Updated last year
Alternatives and similar repositories for mexma
Users that are interested in mexma are comparing it to the libraries listed below
Sorting:
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated 4 months ago
- Code and data from the paper 'Human Feedback is not Gold Standard'☆19Updated last year
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆45Updated 2 years ago
- A repository for research on medium sized language models.☆77Updated last year
- ☆59Updated 2 months ago
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆58Updated this week
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆94Updated last year
- MatFormer repo☆70Updated last year
- Code repository for the paper "MrT5: Dynamic Token Merging for Efficient Byte-level Language Models."☆54Updated 4 months ago
- [COLM 2024] Early Weight Averaging meets High Learning Rates for LLM Pre-training☆19Updated last year
- Improving Text Embedding of Language Models Using Contrastive Fine-tuning☆64Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated last year
- ☆48Updated last year
- ☆56Updated last year
- ☆91Updated last year
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated last year
- 🕸 GlotCC Dataset and Pipline -- NeurIPS 2024☆20Updated 10 months ago
- ☆17Updated 10 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆82Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆35Updated 2 years ago
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆31Updated 8 months ago
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆62Updated 7 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆32Updated last year
- Code for Zero-Shot Tokenizer Transfer☆142Updated last year
- ☆41Updated last year
- ☆29Updated 11 months ago
- ☆57Updated last month
- Code for NeurIPS LLM Efficiency Challenge☆60Updated last year
- SILO Language Models code repository☆83Updated last year