This is a 4-bit quantized version of the Qwen2.5-3B-Instruct model prepared with Unsloth and bitsandbytes. It enables developers to fine-tune LLMs significantly faster and with much lower memory usage compared to standard methods. The model is hosted on Hugging Face and is intended for efficient continued pre-training or instruction tuning.
In the Foundation models & chat space, Qwen2.5 3B Instruct Unsloth Bnb takes a focused approach. It focuses on fine-tuning large language models 2-5x faster while using 70% less memory. Qwen2.5 3B Instruct Unsloth Bnb is an open-source project aimed at developers. The project is open source (Apache-2.0). Qwen2.5 3B Instruct Unsloth Bnb is available on the web, the command line, and API.
It is developed by Unsloth, and the product first shipped in 2023. The project is developed in the open on GitHub with 68.4k stars and 1.2k commits in the last 90 days. Among its 3 catalogued features are 4-bit quantization, fast fine-tuning, and memory efficient training.
Latest indexed changes and source events
unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit verified by the PulseGate indexer
Other apps tracked under the same category.
