kddubey / cappr
Completion After Prompt Probability. Make your LLM make a choice
β69Updated last week
Related projects β
Alternatives and complementary repositories for cappr
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)β68Updated 3 weeks ago
- π Reference-Free automatic summarization evaluation with potential hallucination detectionβ99Updated 9 months ago
- Lightweight demos for finetuning LLMs. Powered by π€ transformers and open-source datasets.β64Updated 2 weeks ago
- Using open source LLMs to build synthetic datasets for direct preference optimizationβ40Updated 8 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).β76Updated 7 months ago
- Python API for https://vespa.ai, the open big data serving engineβ101Updated this week
- Official repo for NAACL 2024 Findings paper "LeTI: Learning to Generate from Textual Interactions."β61Updated last year
- Mixing Language Models with Self-Verification and Meta-Verificationβ97Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)β88Updated 8 months ago
- β91Updated last month
- β91Updated last year
- FastFit β‘ When LLMs are Unfit Use FastFit β‘ Fast and Effective Text Classification with Many Classesβ184Updated last month
- Evaluating LLMs with CommonGen-Liteβ84Updated 7 months ago
- Generalist and Lightweight Model for Text Classificationβ48Updated 2 months ago
- β39Updated 2 weeks ago
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first appβ¦β161Updated 9 months ago
- β46Updated 9 months ago
- [Added T5 support to TRLX] A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)β47Updated last year
- β106Updated 2 weeks ago
- π Datasets and models for instruction-tuningβ231Updated last year
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answersβ122Updated 7 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absoluteβ¦β48Updated 3 months ago
- β123Updated 6 months ago
- Multi-Domain Expert Learningβ67Updated 9 months ago
- Pretraining Efficiently on S2ORC!β136Updated 2 weeks ago
- Classy-fire is multiclass text classification approach leveraging OpenAI LLM model APIs optimally using clever parameter tuning and prompβ¦β72Updated 10 months ago
- Code accompanying "How I learned to start worrying about prompt formatting".β92Updated last month
- β48Updated last year
- Notebooks for training universal 0-shot classifiers on many different tasksβ104Updated 7 months ago