dolphin-2.9.3-mistral-7b-32k-ov

dolphin-2.9.3-mistral-7b-32k-ov is an OpenVino int4 quantized version of Dolphin 2.9.3 Mistral 7B, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

llmware/dolphin-2.9.3-mistral-7b-32k is a leading dialog chat finetune of Mistral 7B.

Model Description

• Developed by: cognitivecomputations
• Model type: mistral
• Parameters: 7 billion
• Model Parent: cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: General purpose dialog and chat
• RAG Benchmark Accuracy Score: NA
• Quantization: int4

Model Card Contact

llmware on hf

llmware website