upgrade to use hon9kon9ize/Cantonese-Llama-2-7B-preview20240903

README.md

@@ -1,13 +1,13 @@
 ---
-title: Cantonese-Llama-2-7B-preview20240625
+title: Cantonese-Llama-2-7B-Preview20240903
 emoji: 🦙
 colorFrom: yellow
 colorTo: pink
 sdk: gradio
-sdk_version: 4.37.2
+sdk_version: 4.42.0
 app_file: app.py
 pinned: false
-license: apache-2.0
+license: cc-by-sa-4.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -12,7 +12,7 @@ DEFAULT_MAX_NEW_TOKENS = 2048
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# hon9kon9ize/Cantonese-Llama-2-7B-preview20240625
+# hon9kon9ize/Cantonese-Llama-2-7B-preview20240903
 
 Please join our [Discord server](https://discord.gg/gG6GPp8XxQ) and give me your feedback
 """
@@ -23,7 +23,7 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "hon9kon9ize/Cantonese-Llama-2-7B-preview20240625"
+    model_id = "hon9kon9ize/Cantonese-Llama-2-7B-preview20240903"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
     model = torch.compile(model)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
@@ -124,4 +124,4 @@ with gr.Blocks() as demo:
     chat_interface.render()
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    demo.queue(max_size=20).launch()