chore: Add Qwen-chat-1_8B-rkllm conversion to README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- qwen
|
| 7 |
+
- qwen-chat-1_8B
|
| 8 |
+
- rkllm
|
| 9 |
+
- rk3588
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Qwen-chat-1_8B-rkllm
|
| 13 |
+
This is a conversion from [Qwen-1_8B-Chat](https://huggingface.co/Qwen/Qwen-1_8B-Chat) to the RKLLM format for chat in Rockchip devices.
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
- [Qwen-chat-1\_8B-rkllm](#qwen-chat-1_8b-rkllm)
|
| 17 |
+
- [Support Devices](#support-devices)
|
| 18 |
+
- [Convert tools](#convert-tools)
|
| 19 |
+
- [Converted with RKLLM runtime](#converted-with-rkllm-runtime)
|
| 20 |
+
- [License](#license)
|
| 21 |
+
- [Reference](#reference)
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
## Support Devices
|
| 25 |
+
* RK3588/RK3588s
|
| 26 |
+
|
| 27 |
+
## Convert tools
|
| 28 |
+
To Converting LLMs for Rockchip's NPUs, please see the artical[^1][^2] for model details.
|
| 29 |
+
|
| 30 |
+
## Converted with RKLLM runtime
|
| 31 |
+
* RKLLM runtime `1.0.1`
|
| 32 |
+
|
| 33 |
+
## License
|
| 34 |
+
Same as the original [Qwen-1_8B-Chat](https://huggingface.co/Qwen/Qwen-1_8B-Chat)
|
| 35 |
+
|
| 36 |
+
## Reference
|
| 37 |
+
[^1]: [airockchip/rknn-llm](https://github.com/airockchip/rknn-llm)
|
| 38 |
+
[^2]: [Pelochus/ezrknn-llm](https://github.com/Pelochus/ezrknn-llm)
|