Knowledgator / utca
Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex programs
☆30Updated 3 weeks ago
Alternatives and similar repositories for utca:
Users that are interested in utca are comparing it to the libraries listed below
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆46Updated 3 weeks ago
- 🤗 HuggingFace Inference Toolkit for Google Cloud Vertex AI (similar to SageMaker's Inference Toolkit, but for Vertex AI and unofficial)☆17Updated last year
- PyTorch implementation for MRL☆18Updated last year
- Pre-train Static Word Embeddings☆58Updated 3 weeks ago
- ☆47Updated last year
- Embedding Recycling for Language models☆38Updated last year
- GraphER: A Structure-aware Text-to-Graph Model for Entity and Relation Extraction☆71Updated 9 months ago
- Generalist and Lightweight Model for Text Classification☆123Updated this week
- Source code and data for Like a Good Nearest Neighbor☆28Updated 3 months ago
- Using short models to classify long texts☆21Updated 2 years ago
- GLiNER model in a FastAPI microservice.☆42Updated 4 months ago
- A Python library aimed at dissecting and augmenting NER training data.☆58Updated last year
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆30Updated 8 months ago
- Efficient few-shot learning with cross-encoders.☆51Updated last year
- A RAG that can scale 🧑🏻💻☆11Updated 11 months ago
- StAtutory Reasoning Assessment☆13Updated 2 years ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆76Updated 6 months ago
- Tool to apply Legal Matter Specification Standard (LMSS) to documents☆13Updated 8 months ago
- ☆41Updated 2 years ago
- Plug-and-play document processing pipelines. No training. Batteries included.☆57Updated last week
- EnriCo: Enriched Representation and Globally Constrained Inference for Entity and Relation Extraction☆24Updated 11 months ago
- Search through Facebook Research's PyTorch BigGraph Wikidata-dataset with the Weaviate vector search engine☆31Updated 3 years ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆19Updated 3 months ago
- ☆45Updated 3 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆48Updated last year
- Resources related to EACL 2023 paper "SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domain…☆52Updated last year
- SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batchi…☆33Updated 11 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- Fact checking baseline combining dense retrieval and textual entailment☆28Updated 3 months ago
- Python library to use Pleias-RAG models☆36Updated this week