wwwaj commited on
Commit
5a9c308
1 Parent(s): 8b03b36

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -4
README.md CHANGED
@@ -105,9 +105,7 @@ tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
105
  messages = [
106
  {"role": "system", "content": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user."},
107
  {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
108
- {"role": "system", "content": "Sure! Here are some ways to eat bananas and dragonfruits together:"},
109
- {"role": "system", "content": "1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey."},
110
- {"role": "system", "content": "2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
111
  {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
112
  ]
113
 
@@ -132,7 +130,7 @@ Note that by default the model use flash attention which requires certain types
132
 
133
  + V100 or earlier generation GPUs: call `AutoModelForCausalLM.from_pretrained()` with `attn_implementation="eager"`
134
  + CPU: use the **GGUF** quantized models [4K](https://aka.ms/Phi3-mini-4k-instruct-gguf)
135
- + Optimized inference: use the **ONNX** models [4K](https://aka.ms/Phi3-mini-4k-instruct-onnx)
136
 
137
  ## Responsible AI Considerations
138
 
 
105
  messages = [
106
  {"role": "system", "content": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user."},
107
  {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
108
+ {"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."},
 
 
109
  {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
110
  ]
111
 
 
130
 
131
  + V100 or earlier generation GPUs: call `AutoModelForCausalLM.from_pretrained()` with `attn_implementation="eager"`
132
  + CPU: use the **GGUF** quantized models [4K](https://aka.ms/Phi3-mini-4k-instruct-gguf)
133
+ + Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [4K](https://aka.ms/Phi3-mini-4k-instruct-onnx)
134
 
135
  ## Responsible AI Considerations
136