|
--- |
|
license_name: tongyi-qianwen-research |
|
license_link: LICENSE |
|
language: |
|
- en |
|
- zh |
|
tags: |
|
- qwen |
|
- rkllm |
|
- rk3588 |
|
- Rockchip |
|
license: other |
|
--- |
|
|
|
# Qwen2-1_5B_rkLLM |
|
|
|
- [English](#qwen2-1_5b_rkllm) |
|
- [中文](#通义千问2-1_5b) |
|
|
|
## Qwen2-1_5B-Chat_rkLLM |
|
|
|
### Introduction |
|
|
|
Qwen2-1_5B-Chat_rkLLM is a model converted from [Qwen2-1_5B](https://huggingface.co/Qwen/Qwen2-1_5B/), optimized for Rockchip devices. This model runs on the NPU of the RK3588 chip. |
|
|
|
- **Model Name**: Qwen2-1_5B |
|
- **Architecture**: Same as Qwen2-1_5B |
|
- **Publisher**: FydeOS |
|
- **Release Date**: May 14, 2024 |
|
|
|
### Model Details |
|
|
|
Qwen2-1_5B-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. |
|
|
|
1. Download the model file `XXX.rkllm`. |
|
2. Create a folder named `model/` and place the model file inside this folder. |
|
3. Launch FydeOS AI and configure the settings on the settings page. |
|
|
|
#### Other OS |
|
|
|
> Ensure you have updated the NPU kernel related to RKLLM. |
|
|
|
1. Download the model file `XXX.rkllm`. |
|
2. Follow the configuration guidelines in the [official documentation](https://github.com/airockchip/rknn-llm). |
|
|
|
### 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2-1_5B |
|
|
|
### 介绍 |
|
|
|
通义千问2-1_5B 是从 [Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) 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**: Qwen2-1_5B |
|
- **模型架构**: 与 Qwen2-1_5B 相同 |
|
- **发布者**: FydeOS |
|
- **发布日期**: 2024-07-12 |
|
|
|
### 模型详情 |
|
|
|
通义千问-1.5B（Qwen2-1_5B）是阿里云研发的通义千问系列大模型中的一员，拥有 15 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。 |
|
|
|
1. 下载模型文件 `XXX.rkllm`。 |
|
2. 新建文件夹 `model/`，将模型文件放置于该文件夹内。 |
|
3. 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。 |
|
|
|
1. 下载模型文件 `XXX.rkllm`。 |
|
2. 按照官方文档进行配置：[官方文档](https://github.com/airockchip/rknn-llm)。 |
|
|
|
### 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 |
