Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
license_name: tongyi-qianwen
|
3 |
license_link: LICENSE
|
4 |
language:
|
5 |
- en
|
@@ -8,13 +8,14 @@ tags:
|
|
8 |
- qwen
|
9 |
- rkllm
|
10 |
- rk3588
|
11 |
-
-
|
|
|
12 |
---
|
13 |
|
14 |
# 通义千问-1_8B / Qwen-1_8B-Chat_rkLLM
|
15 |
|
16 |
-
- [中文](#通义千问-
|
17 |
-
- [English](#
|
18 |
|
19 |
## 通义千问-1_8B
|
20 |
|
@@ -75,7 +76,7 @@ tags:
|
|
75 |
|
76 |
## Qwen-1_8B-Chat_rkLLM
|
77 |
|
78 |
-
|
79 |
|
80 |
Qwen-1_8B-Chat_rkLLM is a model converted from [Qwen-1_8B](https://huggingface.co/Qwen/Qwen-1_8B/), specifically designed for Rockchip devices. This model operates on the NPU of the RK3588 chip.
|
81 |
|
@@ -84,15 +85,15 @@ Qwen-1_8B-Chat_rkLLM is a model converted from [Qwen-1_8B](https://huggingface.c
|
|
84 |
- **Publisher**: FydeOS
|
85 |
- **Release Date**: 14 May 2024
|
86 |
|
87 |
-
|
88 |
|
89 |
Qwen-1_8B-Chat_rkLLM is part of the Tongyi Qianwen series developed by Alibaba Cloud. This large language model features 1.8 billion parameters and is based on the Transformer architecture. It has been pre-trained on a vast and diverse dataset, including web texts, professional literature, and code.
|
90 |
|
91 |
-
|
92 |
|
93 |
This model is only supported on devices with the Rockchip RK3588/s chip. Please verify your device’s chip information and ensure the NPU is operational.
|
94 |
|
95 |
-
|
96 |
|
97 |
> Ensure you have upgraded to the latest version of openFyde.
|
98 |
|
@@ -100,28 +101,28 @@ This model is only supported on devices with the Rockchip RK3588/s chip. Please
|
|
100 |
2. Create a folder named `model/` and place the model file inside this folder.
|
101 |
3. Launch FydeOS AI and configure the settings on the settings page.
|
102 |
|
103 |
-
|
104 |
|
105 |
> Ensure you have updated the NPU kernel related to RKLLM.
|
106 |
|
107 |
1. Download the model file `XXX.rkllm`.
|
108 |
2. Follow the configuration guidelines provided in the [official documentation](https://github.com/airockchip/rknn-llm).
|
109 |
|
110 |
-
|
111 |
|
112 |
For issues, please refer to the issue section. If your problem remains unresolved, submit a new issue.
|
113 |
|
114 |
-
|
115 |
|
116 |
- The model may have performance limitations in certain scenarios.
|
117 |
- Ensure compliance with relevant laws and regulations during usage.
|
118 |
- Parameter tuning might be necessary to achieve optimal performance.
|
119 |
|
120 |
-
|
121 |
|
122 |
This model is licensed under the same terms as [Qwen-1_8B](https://huggingface.co/Qwen/Qwen-1_8B/).
|
123 |
|
124 |
-
|
125 |
|
126 |
For more information, please contact:
|
127 |
|
|
|
1 |
---
|
2 |
+
license_name: tongyi-qianwen-research
|
3 |
license_link: LICENSE
|
4 |
language:
|
5 |
- en
|
|
|
8 |
- qwen
|
9 |
- rkllm
|
10 |
- rk3588
|
11 |
+
- Rockchip
|
12 |
+
license: other
|
13 |
---
|
14 |
|
15 |
# 通义千问-1_8B / Qwen-1_8B-Chat_rkLLM
|
16 |
|
17 |
+
- [中文](#通义千问-1_8b)
|
18 |
+
- [English](#qwen-1_8b-chat_rkllm)
|
19 |
|
20 |
## 通义千问-1_8B
|
21 |
|
|
|
76 |
|
77 |
## Qwen-1_8B-Chat_rkLLM
|
78 |
|
79 |
+
### Introduction
|
80 |
|
81 |
Qwen-1_8B-Chat_rkLLM is a model converted from [Qwen-1_8B](https://huggingface.co/Qwen/Qwen-1_8B/), specifically designed for Rockchip devices. This model operates on the NPU of the RK3588 chip.
|
82 |
|
|
|
85 |
- **Publisher**: FydeOS
|
86 |
- **Release Date**: 14 May 2024
|
87 |
|
88 |
+
### Model Details
|
89 |
|
90 |
Qwen-1_8B-Chat_rkLLM is part of the Tongyi Qianwen series developed by Alibaba Cloud. This large language model features 1.8 billion parameters and is based on the Transformer architecture. It has been pre-trained on a vast and diverse dataset, including web texts, professional literature, and code.
|
91 |
|
92 |
+
### User Guide
|
93 |
|
94 |
This model is only supported on devices with the Rockchip RK3588/s chip. Please verify your device’s chip information and ensure the NPU is operational.
|
95 |
|
96 |
+
#### openFyde
|
97 |
|
98 |
> Ensure you have upgraded to the latest version of openFyde.
|
99 |
|
|
|
101 |
2. Create a folder named `model/` and place the model file inside this folder.
|
102 |
3. Launch FydeOS AI and configure the settings on the settings page.
|
103 |
|
104 |
+
#### Other Systems
|
105 |
|
106 |
> Ensure you have updated the NPU kernel related to RKLLM.
|
107 |
|
108 |
1. Download the model file `XXX.rkllm`.
|
109 |
2. Follow the configuration guidelines provided in the [official documentation](https://github.com/airockchip/rknn-llm).
|
110 |
|
111 |
+
### FAQ
|
112 |
|
113 |
For issues, please refer to the issue section. If your problem remains unresolved, submit a new issue.
|
114 |
|
115 |
+
### Limitations and Considerations
|
116 |
|
117 |
- The model may have performance limitations in certain scenarios.
|
118 |
- Ensure compliance with relevant laws and regulations during usage.
|
119 |
- Parameter tuning might be necessary to achieve optimal performance.
|
120 |
|
121 |
+
### Licence
|
122 |
|
123 |
This model is licensed under the same terms as [Qwen-1_8B](https://huggingface.co/Qwen/Qwen-1_8B/).
|
124 |
|
125 |
+
### Contact Information
|
126 |
|
127 |
For more information, please contact:
|
128 |
|