microsoft / classy-fire
Classy-fire is multiclass text classification approach leveraging OpenAI LLM model APIs optimally using clever parameter tuning and prompting.
β77Updated last year
Alternatives and similar repositories for classy-fire:
Users that are interested in classy-fire are comparing it to the libraries listed below
- Lightweight demos for finetuning LLMs. Powered by π€ transformers and open-source datasets.β76Updated 6 months ago
- Anthropic Claude2 Hackathon:Building MCTS with Claude for optimal action prediction during patient/doctor interactions.β104Updated last year
- WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting.β40Updated 9 months ago
- π Datasets and models for instruction-tuningβ238Updated last year
- Track the progress of LLM context utilisationβ54Updated last week
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answersβ128Updated last year
- We view Large Language Models as stochastic language layers in a network, where the learnable parameters are the natural language promptsβ¦β94Updated 9 months ago
- Leverage your LangChain trace data for fine tuningβ41Updated 8 months ago
- β93Updated 4 months ago
- Advanced Reasoning Benchmark Dataset for LLMsβ45Updated last year
- Completion After Prompt Probability. Make your LLM make a choiceβ76Updated 5 months ago
- Reward Model framework for LLM RLHFβ61Updated last year
- Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"β83Updated 8 months ago
- Code, datasets, models for the paper "Automatic Evaluation of Attribution by Large Language Models"β56Updated last year
- Resources related to EACL 2023 paper "SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domainβ¦β52Updated last year
- This repository implements the chain of verification paper by Meta AIβ168Updated last year
- Large-language Model Evaluation framework with Elo Leaderboard and A-B testingβ52Updated 6 months ago
- create workflows with LLMsβ54Updated 8 months ago
- β47Updated last year
- Explore the use of DSPy for extracting features from PDFs πβ39Updated last year
- Writing Blog Posts with Generative Feedback Loops!β47Updated last year
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 laβ¦β48Updated last year
- π Reference-Free automatic summarization evaluation with potential hallucination detectionβ100Updated last year
- β75Updated last year
- Based on the tree of thoughts paperβ48Updated last year
- Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuningβ46Updated last year
- Source codes for the paper "Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints"β28Updated 2 years ago
- β53Updated 4 months ago
- β145Updated last year
- β24Updated last year