fix multiple typo in README

README.md

@@ -104,9 +104,7 @@ tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
 messages = [
     {"role": "system", "content": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user."},
     {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
-    {"role": "system", "content": "Sure! Here are some ways to eat bananas and dragonfruits together:"},
-    {"role": "system", "content": "1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey."},
-    {"role": "system", "content": "2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
+    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
     {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
 ]
 
@@ -130,8 +128,7 @@ print(output[0]['generated_text'])
 Note that by default the model use flash attention which requires certain types of GPU to run. If you want to run the model on:
 
 + V100 or earlier generation GPUs: call `AutoModelForCausalLM.from_pretrained()`  with `attn_implementation="eager"`
-+ CPU: use the **GGUF** quantized models [4K](https://aka.ms/Phi3-mini-4k-instruct-gguf)
-+ Optimized inference: use the **ONNX** models [4K](https://aka.ms/Phi3-mini-128k-instruct-onnx)
++ Optimized inference: use the **ONNX** models [128K](https://aka.ms/phi3-mini-128k-instruct-onnx)
 
 ## Responsible AI Considerations
 
@@ -157,7 +154,7 @@ Developers should apply responsible AI best practices and are responsible for en
 
 * Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.
 * Inputs: Text. It is best suited for prompts using chat format.
-* Context length: 4K tokens
+* Context length: 128K tokens
 * GPUs: 512 H100-80G
 * Training time: 7 days
 * Training data: 3.3T tokens
@@ -188,7 +185,7 @@ More specifically, we do not change prompts, pick different few-shot examples, c
 
 The number of k–shot examples is listed per-benchmark. 
 
-|   | Phi-3-Mini-4K-In<br>3.8b | Phi-3-Small<br>7b (preview) | Phi-3-Medium<br>14b (preview) | Phi-2<br>2.7b | Mistral<br>7b | Gemma<br>7b | Llama-3-In<br>8b | Mixtral<br>8x7b | GPT-3.5<br>version 1106 |
+|   | Phi-3-Mini-128K-In<br>3.8b | Phi-3-Small<br>7b (preview) | Phi-3-Medium<br>14b (preview) | Phi-2<br>2.7b | Mistral<br>7b | Gemma<br>7b | Llama-3-In<br>8b | Mixtral<br>8x7b | GPT-3.5<br>version 1106 |
 |---|---|---|---|---|---|---|---|---|---|
 | MMLU <br>5-Shot | 68.8 | 75.3 | 78.2 | 56.3 | 61.7 | 63.6 | 66.0 | 68.4 | 71.4 |
 | HellaSwag <br> 5-Shot | 76.7 | 78.7 | 83.2 | 53.6 | 58.5 | 49.8 | 69.5 | 70.4 | 78.8 |