Update README.md

README.md

@@ -8,11 +8,11 @@ datasets:
 - HuggingFaceH4/no_robots
 - Open-Orca/OpenOrca
 language:
-- chs
+- zh
 - en
 ---
 # Zephyr-8x7b:Zephyr Models but Mixtral 8x7B
 
-We present to you the Zephyr-8x7b, a MoE model that SFT-only training on a dataset of nearly four million conversation corpora.
+We present to you the Zephyr-8x7b, a Mixtral 8x7B MoE model that SFT-only training on a dataset of nearly four million conversation corpora.
 
-It has demonstrated strong contextual understanding, reasoning, and human moral alignment without preference alignment, and we invite you to participate in our exploration!
+It has demonstrated strong contextual understanding, reasoning, and human moral alignment without alignment like DPO, and we invite you to participate in our exploration!