Update README.md

README.md

@@ -7,7 +7,8 @@ license: mit
 The Phi-3-22b is a depth upsampled version of the 14b  [Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct). We removed the bottom 8 layers of one copy of the 14b and the top 8 layers of another copy of the 14b model and stacked them. We plan to do continued pretraining to improve performance. 
 Since this model has not been continued pretrained, the quality may vary. 
 ```
-!pip install transformers accelerate 
+!pip install flash-attn --no-build-isolation
+!pip install peft bitsandbytes accelerate transformers
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 tokenizer = AutoTokenizer.from_pretrained("ontocord/phi-3-22b", trust_remote_code=True)
@@ -27,7 +28,7 @@ Imagine, if you will, a vast kingdom stretching beyond the horizon, where countl
 In this kingdom, information flows like a mighty river,...
 ```
 
-In 4-bit
+To run on a Colab T4, try 4-bit
 ```
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch