Qwen-1_8B-Chat_rkLLM
Qwen-1_8B-Chat_rkLLM
Introduction
Qwen-1_8B-Chat_rkLLM is a model converted from Qwen-1_8B, optimized for Rockchip devices. This model runs on the NPU of the RK3588 chip.
- Model Name: Qwen-1_8B
- Architecture: Same as Qwen-1_8B
- Publisher: FydeOS
- Release Date: May 14, 2024
Model Details
Qwen-1_8B-Chat_rkLLM is part of the Tongyi Qianwen series developed by Alibaba. This large language model features 1.8 billion parameters and is based on the Transformer architecture. It has been pre-trained on a diverse dataset, including web texts, professional literature, and code.
User Guide
This model is supported only on devices with the Rockchip RK3588/s chip. Please verify your device’s chip information and ensure the NPU is operational.
openFyde
Ensure you have upgraded to the latest version of openFyde.
- Download the model file
XXX.rkllm
. - Create a folder named
model/
and place the model file inside this folder. - Launch FydeOS AI and configure the settings on the settings page.
Other OS
Ensure you have updated the NPU kernel related to RKLLM.
- Download the model file
XXX.rkllm
. - Follow the configuration guidelines in the official documentation.
Limitations and Considerations
- The model may have performance limitations in certain scenarios.
- Ensure compliance with relevant laws and regulations during usage.
- Parameter tuning might be necessary to achieve optimal performance.
通义千问-1_8B
介绍
通义千问-1_8B 是从 Qwen-1_8B 转换而来的 RKLLM 模型,专为 Rockchip 设备优化。该模型运行于 RK3588 的 NPU 上。
- 模型名称: Qwen-1_8B
- 模型架构: 与 Qwen-1_8B 相同
- 发布者: FydeOS
- 发布日期: 2024-05-14
模型详情
通义千问-1_8B(Qwen-1_8B)是阿里云研发的通义千问系列大模型中的一员,拥有 18 亿参数。该模型基于 Transformer 架构,经过大规模预训练,涵盖了多种类型的数据,包括网络文本、专业书籍和代码。
使用指南
此模型仅支持搭载 Rockchip RK3588/s 芯片的设备。请确认设备信息并确保 NPU 可用。
openFyde 系统
请确保你已将系统升级到最新版本。
- 下载模型文件
XXX.rkllm
。 - 新建文件夹
model/
,将模型文件放置于该文件夹内。 - 启动 FydeOS AI,在设置页面进行相关配置。
其它系统
请确保已完成 RKLLM 的 NPU 相关内核更新。
- 下载模型文件
XXX.rkllm
。 - 按照官方文档进行配置:官方文档。
限制与注意事项
- 模型在某些情况下可能存在性能限制
- 使用时请遵循相关法律法规
- 可能需要进行适当的参数调优以达到最佳效果