RulinShao / massive-serveLinks
Python package for serving a local search engine. One command to download and serve a datastore---that's it π.
β21Updated 2 weeks ago
Alternatives and similar repositories for massive-serve
Users that are interested in massive-serve are comparing it to the libraries listed below
Sorting:
- β38Updated last year
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Trainingβ22Updated 10 months ago
- β51Updated last year
- [arXiv preprint] Official Repository for "Evaluating Language Models as Synthetic Data Generators"β33Updated 6 months ago
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructionsβ44Updated 11 months ago
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curationβ55Updated last month
- Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"β77Updated 2 years ago
- Code and data for paper "Context-faithful Prompting for Large Language Models".β40Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 laβ¦β48Updated last year
- Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators (Liu et al.; COLM 2024)β47Updated 5 months ago
- Codebase for Instruction Following without Instruction Tuningβ34Updated 9 months ago
- Code for paper 'Data-Efficient FineTuning'β29Updated 2 years ago
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrievalβ50Updated this week
- Exploration of automated dataset selection approaches at large scales.β45Updated 3 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flβ¦β75Updated 10 months ago
- Pile Deduplication Codeβ19Updated 2 years ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messagesβ48Updated 6 months ago
- β45Updated 10 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our focβ¦β32Updated last year
- β74Updated last year
- Findings of ACL'2023: Optimizing Test-Time Query Representations for Dense Retrievalβ30Updated last year
- β29Updated 11 months ago
- β44Updated 9 months ago
- Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"β37Updated 10 months ago
- Retrieval as Attentionβ82Updated 2 years ago
- Long Context Extension and Generalization in LLMsβ57Updated 9 months ago
- β64Updated last year
- Suri: Multi-constraint instruction following for long-form text generation (EMNLPβ24)β23Updated 7 months ago
- Revisiting Mid-training in the Era of RL Scalingβ56Updated 2 months ago
- Scalable Meta-Evaluation of LLMs as Evaluatorsβ42Updated last year