ericrisco
/

flor-1-3B-customerservice

Text Generation

customer service

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

ericrisco commited on Feb 2, 2024

Commit

d1a3a99

·

verified ·

1 Parent(s): 00c4e0c

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -86,11 +86,11 @@ Com puc accedir a la meva factura?
 - Custom prompts are created to structure the input and output in a way that is beneficial for a customer service chatbot.
 - Each prompt includes:
-  - Beginning of the sequence token (`<s>`)
   - Instruction text (defining the role and language of the model)
   - Input text (customer's message)
   - Expected response text
-  - End of the sequence token (`</s>`)
 ### Training Process

 - Custom prompts are created to structure the input and output in a way that is beneficial for a customer service chatbot.
 - Each prompt includes:
+  - Beginning of the sequence token (`<|startoftext|>`)
   - Instruction text (defining the role and language of the model)
   - Input text (customer's message)
   - Expected response text
+  - End of the sequence token (`<|endoftext|>`)
 ### Training Process