Commit
•
b36bc7b
1
Parent(s):
50540d5
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
license_name: tongyi-qianwen-research
|
| 4 |
-
license_link: https://huggingface.co/Qwen/Qwen1.5-
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
pipeline_tag: text-generation
|
|
@@ -40,7 +40,7 @@ We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and
|
|
| 40 |
## How to use
|
| 41 |
Cloning the repo may be inefficient, and thus you can manually download the GGUF file that you need or use `huggingface-cli` (`pip install huggingface_hub`) as shown below:
|
| 42 |
```shell
|
| 43 |
-
huggingface-cli download Qwen/Qwen1.5-
|
| 44 |
```
|
| 45 |
|
| 46 |
We demonstrate how to use `llama.cpp` to run Qwen1.5:
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
license_name: tongyi-qianwen-research
|
| 4 |
+
license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/blob/main/LICENSE
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
pipeline_tag: text-generation
|
|
|
|
| 40 |
## How to use
|
| 41 |
Cloning the repo may be inefficient, and thus you can manually download the GGUF file that you need or use `huggingface-cli` (`pip install huggingface_hub`) as shown below:
|
| 42 |
```shell
|
| 43 |
+
huggingface-cli download Qwen/Qwen1.5-1.8B-Chat-GGUF qwen1_5-1_8b-chat-q8_0.gguf --local-dir . --local-dir-use-symlinks False
|
| 44 |
```
|
| 45 |
|
| 46 |
We demonstrate how to use `llama.cpp` to run Qwen1.5:
|