Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Robust recipes to align language models with human and AI preferences
Ongoing research training transformer models at scale
🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.
The Triton TensorRT-LLM Backend
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Tools for merging pretrained large language models.
Merge Transformers language models by use of gradient parameters.
DeepSeek Coder: Let the Code Write Itself
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
A pure Unix shell script implementing ACME client protocol
A high-throughput and memory-efficient inference and serving engine for LLMs
The code for the paper C3: Zero-shot Text-to-SQL with ChatGPT
Home of StarCoder: fine-tuning & inference!
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Repo for counting stars and contributing. Press F to pay respect to glorious developers.