DunZhang / StellaLinks
β62Updated 11 months ago
Alternatives and similar repositories for Stella
Users that are interested in Stella are comparing it to the libraries listed below
Sorting:
- Lightweight demos for finetuning LLMs. Powered by π€ transformers and open-source datasets.β77Updated 8 months ago
- Codebase accompanying the Summary of a Haystack paper.β78Updated 9 months ago
- Code for KaLM-Embedding modelsβ78Updated 3 months ago
- β57Updated 8 months ago
- [EMNLP 2024] A Retrieval Benchmark for Scientific Literature Searchβ89Updated 6 months ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)β75Updated 8 months ago
- π’ Data Toolkit for Sailor Language Modelsβ92Updated 3 months ago
- Model implementation for the contextual embeddings projectβ33Updated 2 weeks ago
- Source code of the paper: RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering [Fβ¦β66Updated last year
- β47Updated 4 months ago
- Data preparation code for CrystalCoder 7B LLMβ45Updated last year
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).β80Updated last year
- Using open source LLMs to build synthetic datasets for direct preference optimizationβ64Updated last year
- β45Updated 10 months ago
- minimal pytorch implementation of bm25 (with sparse tensors)β101Updated last year
- LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)β137Updated 7 months ago
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrievalβ52Updated last year
- β46Updated 4 months ago
- Retrieval Augmented Generation Generalized Evaluation Datasetβ53Updated 7 months ago
- The first dense retrieval model that can be prompted like an LMβ73Updated last month
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignmentβ57Updated 9 months ago
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructionsβ44Updated 11 months 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
- Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Modelsβ21Updated 3 weeks ago
- Code and Data for "Language Modeling with Editable External Knowledge"β33Updated last year
- AIR-Bench: Automated Heterogeneous Information Retrieval Benchmarkβ144Updated 6 months ago
- β32Updated 7 months ago
- β20Updated 2 months ago
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answersβ129Updated last year
- β71Updated last year