facebookresearch / LIGHT
LIGHT is a platform for text-situated dialogue research. We originally hosted LIGHT as a live game with dialogue models in a grounded setting. This repo contains all of the code to get the LIGHT game running, as well as reproducible code for the research projects along the way of getting LIGHT to where it was.
☆68Updated last year
Related projects ⓘ
Alternatives and complementary repositories for LIGHT
- Official code for ACL 2023 (short, findings) paper "Recursion of Thought: A Divide and Conquer Approach to Multi-Context Reasoning with L…☆42Updated last year
- ☆46Updated last month
- ☆37Updated last year
- ☆111Updated last month
- SCREWS: A Modular Framework for Reasoning with Revisions☆26Updated last year
- ☆91Updated 7 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆25Updated last year
- Experiments with generating opensource language model assistants☆97Updated last year
- Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI☆91Updated last year
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆68Updated last year
- Advanced Reasoning Benchmark Dataset for LLMs☆45Updated 11 months ago
- ☆28Updated 7 months ago
- ☆47Updated last year
- Small and Efficient Mathematical Reasoning LLMs☆71Updated 9 months ago
- Evaluating LLMs with CommonGen-Lite☆84Updated 7 months ago
- ☆86Updated 5 months ago
- Reimplementation of the task generation part from the Alpaca paper☆118Updated last year
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆68Updated 3 weeks ago
- Code repository for the c-BTM paper☆105Updated last year
- Multi-Domain Expert Learning☆67Updated 9 months ago
- Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA☆101Updated 3 months ago
- ☆30Updated last month
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers☆122Updated 7 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆44Updated last month
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆39Updated 10 months ago
- [ICLR 2023] Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners☆111Updated 2 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆41Updated 9 months ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆22Updated 8 months ago