Update the link for qwen2 (#2068)

* Update the link for qwen2

* Fix Qwen2 model URL in model table

* Fix too eager staging

---------

Co-authored-by: Daniël de Kok <[email protected]>

Author: xianbaoqian

docs/source/supported_models.md

@@ -20,7 +20,7 @@ Text Generation Inference enables serving optimized models on specific hardware
 - [Baichuan](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat)
 - [Falcon](https://huggingface.co/tiiuae/falcon-7b-instruct)
 - [StarCoder 2](https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1)
-- [Qwen 2](https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1)
+- [Qwen 2](https://huggingface.co/collections/Qwen/qwen2-6659360b33528ced941e557f)
 - [Opt](https://huggingface.co/facebook/opt-6.7b)
 - [T5](https://huggingface.co/google/flan-t5-xxl)
 - [Galactica](https://huggingface.co/facebook/galactica-120b)

server/text_generation_server/models/__init__.py

@@ -196,7 +196,7 @@ class ModelType(enum.Enum):
     QWEN2 = {
         "type": "qwen2",
         "name": "Qwen 2",
-        "url": "https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1",
+        "url": "https://huggingface.co/collections/Qwen/qwen2-6659360b33528ced941e557f",
     }
     OPT = {
         "type": "opt",