Qwen Chat (14B): A Powerful Language Model for Engaging Conversations

Basic Information

• Model Name: Qwen
• Developer/Creator: Alibaba Cloud
• Release Date: 2023
• Version: Chat 14B
• Model Type: Text-based LLM

Description

Overview

Qwen Chat (14B) is a large language model developed by Alibaba's Cloud Team for engaging conversations. It is part of the Qwen series, which includes base pretrained language models and chat models fine-tuned with human alignment techniques like supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF).

Key Features

• Advanced tool-use and planning capabilities for creating agent applications
• Impressive performance on complex tasks like utilizing a code interpreter

Intended Use

Qwen Chat (14B) is designed for scenarios requiring natural language interactions, such as chatbots, virtual assistants, and language understanding applications.

Language Support

The model supports multiple languages, with strong performance in Chinese.

Technical Details

Architecture

Qwen Chat (14B) uses a transformer-based architecture, a common approach for large language models.

Training Data

The model was trained on up to 3T tokens of diverse texts and codes, covering a wide range of areas.

Performance Metrics

Usage

API Usage Example

License Type

The model's license type is Tongyi Qianwen.