microsoft / classy-fire
Classy-fire is multiclass text classification approach leveraging OpenAI LLM model APIs optimally using clever parameter tuning and prompting.
β72Updated 9 months ago
Related projects: β
- Completion After Prompt Probability. Make your LLM make a choiceβ68Updated last week
- π Reference-Free automatic summarization evaluation with potential hallucination detectionβ99Updated 8 months ago
- Official repo for NAACL 2024 Findings paper "LeTI: Learning to Generate from Textual Interactions."β60Updated last year
- Lightweight demos for finetuning LLMs. Powered by π€ transformers and open-source datasets.β64Updated 2 months ago
- Reward Model framework for LLM RLHFβ56Updated last year
- Writing Blog Posts with Generative Feedback Loops!β41Updated 6 months ago
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answersβ118Updated 6 months ago
- Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuningβ40Updated 9 months ago
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created byβ¦β27Updated 3 weeks ago
- Codebase accompanying the Summary of a Haystack paper.β65Updated 2 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 2 months ago
- Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on taskβ¦β117Updated 3 weeks ago
- Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.β101Updated last week
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).β73Updated 6 months ago
- π Datasets and models for instruction-tuningβ228Updated 11 months ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)β67Updated 2 months ago
- Dense X Retrieval: What Retrieval Granularity Should We Use?β120Updated 8 months ago
- Attribute (or cite) statements generated by LLMs back to in-context information.β107Updated 2 weeks ago
- Track the progress of LLM context utilisationβ53Updated 2 months ago
- Retrieval Augmented Generation Generalized Evaluation Datasetβ51Updated this week
- Generalist and Lightweight Model for Text Classificationβ29Updated 2 weeks ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracyβ93Updated 5 months ago
- β43Updated 7 months ago
- Small and Efficient Mathematical Reasoning LLMsβ69Updated 7 months ago
- AuditNLG: Auditing Generative AI Language Modeling for Trustworthinessβ94Updated last year
- β91Updated 5 months ago
- Code repo for "Agent Instructs Large Language Models to be General Zero-Shot Reasoners"β68Updated last week
- Datasets collection and preprocessings framework for NLP extreme multitask learningβ143Updated 2 months ago
- β45Updated 3 months ago
- Notebooks for training universal 0-shot classifiers on many different tasksβ100Updated 5 months ago