CaaretAI

Qwen2.5-7B-Instruct-caaret

README

License: apache-2.0

Caaret-certified mixed INT7/FP8 checkpoint of Qwen2.5-7B-Instruct for Caaret vLLM mining (PoUW) + chat.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

CaaretAI

Model Tree

Base

Qwen/Qwen2.5-7B-Instruct

Quantized

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints