facebookresearch / PostText
PostText is a QA system for querying your text data. When appropriate structured views are in place, PostText is good at answering queries that require computing aggregates over your data.
☆31Updated last year
Alternatives and similar repositories for PostText:
Users that are interested in PostText are comparing it to the libraries listed below
- Code repository for the paper - "AdANNS: A Framework for Adaptive Semantic Search"☆63Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated last year
- code for paper "Accessing higher dimensions for unsupervised word translation"☆21Updated last year
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated last week
- This is the repository for TimelineQA, a benchmark for querying lifelogs.☆23Updated last year
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆49Updated 9 months ago
- Implementation of "Efficient Multi-vector Dense Retrieval with Bit Vectors", ECIR 2024☆60Updated 5 months ago
- Utilities for Training Very Large Models☆58Updated 6 months ago
- A dashboard for exploring timm learning rate schedulers☆19Updated 4 months ago
- ☆8Updated last year
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆41Updated 11 months ago
- Experimental scripts for researching data adaptive learning rate scheduling.☆23Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 5 months ago
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…☆42Updated last year
- LLMs as Collaboratively Edited Knowledge Bases☆45Updated last year
- Index of URLs to pdf files all over the internet and scripts☆23Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Efficient and Scalable Estimation of Tool Representations in Vector Space☆22Updated 6 months ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- Code for our paper Resources and Evaluations for Multi-Distribution Dense Information Retrieval☆14Updated last year
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆31Updated last year
- Using FlexAttention to compute attention with different masking patterns☆42Updated 6 months ago
- ANE accelerated embedding models!☆17Updated 3 months ago
- Training hybrid models for dummies.☆20Updated 2 months ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆76Updated 5 months ago
- Data preparation code for CrystalCoder 7B LLM☆44Updated 10 months ago
- ☆37Updated 2 years ago
- ☆48Updated last year
- 👷 Build compute kernels☆17Updated this week
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆14Updated last year