Ziyú Ye's repositories
Awesome-Information-Bottleneck
This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.
agent-search
AgentSearch, by SciPhi, is a powerful agent-first rag-client and search engine.
camel
🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
Conformers
Unofficial implementation of Conformal Language Modeling by Quach et al
doc-storygen-v2
Codebase for LLM story generation; updated version of https//github.com/yangkevin2/doc-story-generation
easy-to-hard
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
gemma
Open weights LLM from Google DeepMind.
ijepa
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
Lets-Verify-Step-by-Step
"Improving Mathematical Reasoning with Process Supervision" by OPENAI
llemma_formal2formal
Llemma formal2formal (tactic prediction) theorem proving experiments
LLM_Tree_Search
The official implementation of paper: Alphazero-like Tree-Search can guide large language model decoding and training
magicoder
Magicoder: Source Code Is All You Need
mctx
Monte Carlo tree search in JAX
mechanics-of-proof
Lecture notes for a course on writing proofs, on paper and in the Lean proof assistant
ntptutorial
Tutorial on neural theorem proving
openai-cookbook
Examples and guides for using the OpenAI API
ReProver
Retrieval-Augmented Theorem Provers for Lean
scalax
A simple library for scaling up JAX programs
search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
theorem-proving-reasoning
Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf
trlx-pythia
Finetune Pythia models using TRLx library with Anthropic helpful dataset
vampire
The Vampire Theorem Prover
vissl-probe
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.