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
Related projects ⓘ
Alternatives and complementary repositories for PostText
- 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
- 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
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- Utilities for Training Very Large Models☆56Updated last month
- Open sourced backend for Martian's LLM Inference Provider Leaderboard☆17Updated 3 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆44Updated last year
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated last week
- ☆27Updated 5 months ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated last year
- Code repository for the paper - "AdANNS: A Framework for Adaptive Semantic Search"☆60Updated last year
- Improving Text Embedding of Language Models Using Contrastive Fine-tuning☆59Updated 3 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆37Updated 7 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 7 months ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆61Updated last month
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated last month
- Benchmark for machine learning model online serving (LLM, embedding, Stable-Diffusion, Whisper)☆27Updated last year
- ☆18Updated 9 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Index of URLs to pdf files all over the internet and scripts☆21Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- DPO, but faster 🚀☆23Updated 3 weeks ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 8 months ago
- Github repo for Peifeng's internship project☆12Updated last year
- PyTorch building blocks for OLMo☆18Updated this week
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.☆20Updated 5 months ago
- A dashboard for exploring timm learning rate schedulers☆18Updated last year
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆37Updated 5 months ago