Commit
·
0392df9
1
Parent(s):
74b1a7b
upload files
Browse files
README.md
CHANGED
|
@@ -9,3 +9,8 @@ base_model:
|
|
| 9 |
---
|
| 10 |
|
| 11 |
[GaLLM-14B-v0.1](https://huggingface.co/CjangCjengh/GaLLM-14B-v0.1)的GPTQ-Int4量化版,使用方法相同
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
[GaLLM-14B-v0.1](https://huggingface.co/CjangCjengh/GaLLM-14B-v0.1)的GPTQ-Int4量化版,使用方法相同
|
| 12 |
+
|
| 13 |
+
推荐使用vllm部署,然后使用OpenAI格式的API访问:
|
| 14 |
+
```sh
|
| 15 |
+
vllm serve CjangCjengh/GaLLM-14B-v0.1-GPTQ-Int4 --port <your_port>
|
| 16 |
+
```
|