Update README.md

README.md

@@ -36,7 +36,7 @@ USER:{user's question}<|endoftext|>ASSISTANT:
 ## Model Description
 - **Developed by:** [https://www.tii.ae](https://www.tii.ae);
 - **Finetuned by:** [Virtual Interactive](https://vilm.org);
-- **Language(s) (NLP):** English, German, Spanish, French, Portugese, Russian, Italian, Vietnamese, Indonesian, Chinese, Japanese and Chinese;
+- **Language(s) (NLP):** English, German, Spanish, French, Portugese, Russian, Italian, Vietnamese, Indonesian, Chinese, Japanese and Chinese
 - **Training Time:** 3,000 A100 Hours
 
 ### Out-of-Scope Use
@@ -53,7 +53,7 @@ We recommend users of Vulture-40B to consider finetuning it for the specific set
 
 ## How to Get Started with the Model
 
-To run inference with the model in full `bfloat16` precision you need approximately 8xA100 80GB or equivalent.
+To run inference with the model in full `bfloat16` precision you need approximately 4xA100 80GB or equivalent.
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM