thoppe / The-Pile-PhilPapers
Download, parse, and filter data from Phil Papers. Data-ready for The-Pile.
☆16Updated last year
Alternatives and similar repositories for The-Pile-PhilPapers
Users that are interested in The-Pile-PhilPapers are comparing it to the libraries listed below
Sorting:
- BPE modification that implements removing of the intermediate tokens during tokenizer training.☆25Updated 5 months ago
- ☆33Updated 10 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆57Updated 8 months ago
- Pre-train Static Word Embeddings☆60Updated last month
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆31Updated last year
- Learning to route instances for Human vs AI Feedback☆23Updated 3 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- ☆48Updated 6 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆19Updated 3 months ago
- Aioli: A unified optimization framework for language model data mixing☆25Updated 4 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆48Updated last week
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.☆40Updated 2 months ago
- Embedding Recycling for Language models☆38Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆44Updated last year
- Code for our EMNLP '22 paper "Fixing Model Bugs with Natural Language Patches"☆19Updated 2 years ago
- Minimum Description Length probing for neural network representations☆19Updated 3 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆57Updated 7 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated last month
- ☆12Updated 5 months ago
- ☆23Updated last month
- https://footprints.baulab.info☆17Updated 7 months ago
- Code for SaGe subword tokenizer (EACL 2023)☆24Updated 5 months ago
- Exploring limitations of LLM-as-a-judge☆16Updated 9 months ago
- ☆20Updated 2 months ago
- Code repo for "Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers" (ACL 2023)☆22Updated last year
- ☆22Updated 3 months ago
- ☆15Updated last month
- A guide to structured generation using constrained decoding☆11Updated 11 months ago
- Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.☆25Updated last year