Weni/WeniGPT-Mistral-7B-instructBase-4bit
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Oct 9, 2023Architecture:Transformer0.0K Cold

Weni/WeniGPT-Mistral-7B-instructBase-4bit is a 7 billion parameter instruction-tuned language model developed by Weni, based on the Mistral architecture. This model is specifically trained with 4-bit quantization using bitsandbytes, employing nf4 quantization and double quantization for efficient deployment. It is optimized for tasks requiring a compact yet capable instruction-following model, making it suitable for resource-constrained environments.

Loading preview...