Update

README.md

@@ -1,5 +1,5 @@
 ---
-title: Zephyr 7b Alpha
+title: Zephyr 7b
 emoji: 📉
 colorFrom: green
 colorTo: yellow
@@ -11,4 +11,6 @@ license: mit
 suggested-hardware: t4-small
 ---
 
+https://arxiv.org/abs/2310.16944
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -9,7 +9,7 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-DESCRIPTION = "# Zephyr-7B-alpha"
+DESCRIPTION = "# Zephyr-7B beta"
 
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
@@ -19,7 +19,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available():
-    model_id = "HuggingFaceH4/zephyr-7b-alpha"
+    model_id = "HuggingFaceH4/zephyr-7b-beta"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)