4N3MONE
Follow
Stars
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
PygmalionAI's large-scale inference engine
Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing"
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
Doing simple retrieval from LLM models at various context lengths to measure accuracy
[ACL 2024] LangBridge: Multilingual Reasoning Without Multilingual Supervision
Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI
Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"
All Algorithms implemented in Python
Build resilient language agents as graphs.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
llama3 implementation one matrix multiplication at a time
ReFT: Representation Finetuning for Language Models
Evaluate your LLM's response with Prometheus and GPT4 💯
Comparison of Language Model Inference Engines
A collection of localized (Korean) AWS AI/ML workshop materials for hands-on labs.
⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.
1-Click is all you need.
Official repo for "Make Your LLM Fully Utilize the Context"
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
(NeurIPS 2023 workshop on SoLaR) Korean Multi-task Text Dataset for Classifying Biased Speech in Real-World Online Services