Avmb / inverse_scaling_prize_code_identifier_swap
Submission to the inverse scaling prize
☆23Updated last year
Related projects ⓘ
Alternatives and complementary repositories for inverse_scaling_prize_code_identifier_swap
- Minimum Description Length probing for neural network representations☆16Updated last week
- ☆30Updated last month
- 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 he…☆31Updated last year
- Repository for Skill Set Optimization☆12Updated 3 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆41Updated 9 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆22Updated 7 months ago
- ☆45Updated 9 months ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated last year
- [ICML 2023] "Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation", Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, …☆36Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆25Updated last year
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated this week
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆29Updated this week
- Efficiently computing & storing token n-grams from large corpora☆15Updated last month
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆44Updated 9 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆44Updated 11 months ago
- ☆46Updated last month
- Code repo for "Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers" (ACL 2023)☆22Updated last year
- This repository contains the ToolSelect dataset which was used to fine-tune Llama-2 70B for tool selection.☆17Updated 7 months ago
- ☆24Updated last month
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆19Updated last year
- BPE modification that implements removing of the intermediate tokens during tokenizer training.☆21Updated 2 months ago
- ☆27Updated last year
- ☆25Updated 11 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated this week
- ☆68Updated 2 months ago
- Embedding Recycling for Language models☆38Updated last year