iPieter / universal-distillationLinks
π§ͺCreate domain-adapted language models by distilling from many pre-trained LMs
β10Updated 2 years ago
Alternatives and similar repositories for universal-distillation
Users that are interested in universal-distillation are comparing it to the libraries listed below
Sorting:
- β15Updated 2 months ago
- β24Updated 9 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelβ43Updated last year
- Minimum Description Length probing for neural network representationsβ19Updated 4 months ago
- This repo contains code for the paper "Psychologically-informed chain-of-thought prompts for metaphor understanding in large language modβ¦β14Updated 2 years ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response formatβ27Updated last year
- Repository for Skill Set Optimizationβ13Updated 10 months ago
- β25Updated 2 years ago
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuningβ35Updated last year
- β20Updated last month
- A framework for pitting LLMs against each other in an evolving library of games ββ32Updated last month
- Starbucks: Improved Training for 2D Matryoshka Embeddingsβ20Updated 4 months ago
- Code and Dataset for Learning to Solve Complex Tasks by Talking to Agentsβ24Updated 3 years ago
- The code implementation of MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Modelsβ¦β34Updated last year
- This repository includes a benchmark and code for the paper "Evaluating LLMs at Detecting Errors in LLM Responses".β29Updated 9 months ago
- Search through Facebook Research's PyTorch BigGraph Wikidata-dataset with the Weaviate vector search engineβ31Updated 3 years ago
- β22Updated 4 months ago
- β23Updated 3 months ago
- Plancraft is a minecraft environment and agent suite to test planning capabilities in LLMsβ15Updated 3 weeks ago
- Aioli: A unified optimization framework for language model data mixingβ27Updated 4 months ago
- Official Repository for "Hypencoder: Hypernetworks for Information Retrieval"β25Updated 3 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignmentβ57Updated 9 months ago
- Tasks for describing differences between text distributions.β16Updated 9 months ago
- Mixture of Expert (MoE) techniques for enhancing LLM performance through expert-driven prompt mapping and adapter combinations.β12Updated last year
- β14Updated 8 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our focβ¦β32Updated 11 months ago
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorchβ29Updated last week
- Plug-and-play Search Interfaces with Pyserini and Hugging Faceβ32Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found heβ¦β31Updated last year
- Reasoning by Communicating with Agentsβ28Updated last month