Stars
Unofficial implementation of LSQ-Net, a neural network quantization framework
A simple REPL for Lean 4, returning information about errors and sorries.
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
Neural theorem proving toolkit: data extraction tools for Lean 4
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
The official repository for the paper Multilingual Mathematical Autoformalization
[COLM 2024] A Survey on Deep Learning for Theorem Proving
Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
This is the latest version of textbook《大数理论》(Googology).
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
State-of-the-art bilingual open-sourced Math reasoning LLMs.
A quick guide (especially) for trending instruction finetuning datasets
A reading list on LLM based Synthetic Data Generation 🔥
A native PyTorch Library for large model training
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Must-read Papers on Large Language Model (LLM) Continual Learning
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
The official code of the paper "InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct"(https://arxiv.org/abs/2407.05700).
Controlled Text Generation via Language Model Arithmetic
CodeRAG-Bench: Can Retrieval Augment Code Generation?
Instruct-tune LLaMA on consumer hardware