qdrant / quaterion-modelsLinks
The collection of bulding blocks building fine-tunable metric learning models
β33Updated 2 weeks ago
Alternatives and similar repositories for quaterion-models
Users that are interested in quaterion-models are comparing it to the libraries listed below
Sorting:
- π€ Disaggregators: Curated data labelers for in-depth analysis.β67Updated 2 years ago
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.β33Updated last month
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.β96Updated 2 years ago
- Alternate Implementation for Zero Shot Text Classification: Instead of reframing NLI/XNLI, this reframes the text backbone of CLIP modelsβ¦β37Updated 3 years ago
- [WIP] Behold, semantic-search, built over sentence-transformers to make it easy for search engineers to evaluate, optimise and deploy modβ¦β15Updated 2 years ago
- NLP Examples using the π€ librariesβ40Updated 4 years ago
- β28Updated 2 years ago
- Embedding Recycling for Language modelsβ38Updated 2 years ago
- Our open source implementation of MiniLMv2 (https://aclanthology.org/2021.findings-acl.188)β61Updated 2 years ago
- ππ€ A collection of templates for Hugging Face Spacesβ35Updated 2 years ago
- β43Updated 2 years ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning Pβ¦β35Updated 2 years ago
- A library for squeakily cleaning and filtering language datasets.β47Updated 2 years ago
- Tutorial to pretrain & fine-tune a π€ Flax T5 model on a TPUv3-8 with GCPβ58Updated 3 years ago
- This project shows how to derive the total number of training tokens from a large text dataset from π€ datasets with Apache Beam and Dataβ¦β27Updated 3 years ago
- β15Updated last year
- β13Updated 10 months ago
- Pre-train Static Word Embeddingsβ87Updated last month
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created byβ¦β33Updated last year
- Open source library for few shot NLPβ78Updated 2 years ago
- π οΈ Tools for Transformers compression using PyTorch Lightning β‘β85Updated 3 weeks ago
- Tools for merging pretrained large language models.β19Updated last year
- Scripts to convert datasets from various sources to Hugging Face Datasets.β57Updated 3 years ago
- Adversarial Training and SFT for Bot Safety Modelsβ40Updated 2 years ago
- Supervised instruction finetuning for LLM with HF trainer and Deepspeedβ36Updated 2 years ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrievalβ29Updated 3 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 laβ¦β49Updated last year
- Helper scripts and notes that were used while porting various nlp modelsβ48Updated 3 years ago
- Open Source Speech Inferencing Libary for Indic Languagesβ13Updated 3 years ago
- β22Updated 3 years ago