A series of large language models trained from scratch by developers @01-ai

Locating and editing factual associations in GPT (NeurIPS 2022)

State-of-the-art LLM-based translation models.

Influence Analysis and Estimation - Survey, Papers, and Taxonomy

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Codebase for Merging Language Models (ICML 2024)

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

[SIGIR'24] The official implementation code of MOELoRA.

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models

Minimalist ML framework for Rust

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Scale LLM Engine public repository

Customizable implementation of the self-instruct paper.

Mixture of Expert (MoE) techniques for enhancing LLM performance through expert-driven prompt mapping and adapter combinations.

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

Feeling confused about super alignment? Here is a reading list

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

An Efficient "Factory" to Build Multiple LoRA Adapters

Instruct-tune LLaMA on consumer hardware

Development repository for the Triton language and compiler

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Accessible large language models via k-bit quantization for PyTorch.

Benchmark baseline for retrieval qa applications