Knowledgator / FlashDeBERTaLinks
Trully flash implementation of DeBERTa disentangled attention mechanism.
☆65Updated this week
Alternatives and similar repositories for FlashDeBERTa
Users that are interested in FlashDeBERTa are comparing it to the libraries listed below
Sorting:
- Pre-train Static Word Embeddings☆85Updated 3 weeks ago
- ☆49Updated 7 months ago
- Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex progr …☆33Updated last month
- Using open source LLMs to build synthetic datasets for direct preference optimization☆66Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last year
- Generalist and Lightweight Model for Text Classification☆161Updated 3 months ago
- Python library to use Pleias-RAG models☆62Updated 5 months ago
- PyLate efficient inference engine☆64Updated 3 weeks ago
- PyTorch implementation for MRL☆19Updated last year
- Using short models to classify long texts☆21Updated 2 years ago
- Efficient few-shot learning with cross-encoders.☆60Updated last year
- ☆71Updated 2 months ago
- A massively multilingual modern encoder language model☆91Updated last week
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆33Updated last week
- Model implementation for the contextual embeddings project☆36Updated 4 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- NLP with Rust for Python 🦀🐍☆65Updated 4 months ago
- ☆48Updated last year
- ☆58Updated 4 months ago
- Datamodels for hugging face tokenizers☆76Updated last week
- Embedding Recycling for Language models☆39Updated 2 years ago
- Supercharge huggingface transformers with model parallelism.☆77Updated 2 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆21Updated 3 months ago
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆32Updated last year
- ☆52Updated 8 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated last year
- ☆83Updated 4 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆46Updated 2 months ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆75Updated 11 months ago