tiny-dolphin-2.8-1.1b-ov

tiny-dolphin-2.8-1.1b-ov is an OpenVino int4 quantized version of Tiny Dolphin 2.8, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

tiny-dolphin-2.8-1.1b is a leading dialog chat finetune of Tiny Llama.

Model Description

• Developed by: cognitivecomputations
• Quantized by: llmware
• Model type: tiny llama
• Parameters: 1.1 billion
• Model Parent: cognitivecomputations/TinyDolphin-2.8-1.1b
• 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