Re-add end of text

openapi.yaml

@@ -2476,8 +2476,8 @@ components:
  description: &completions_prompt_description |
  The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
 
- Note that is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.
- default: ""
+ Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.
+ default: "<|endoftext|>"
  nullable: true
  oneOf:
  - type: string
@@ -2541,7 +2541,7 @@ components:
 
  Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
 
- As an example, you can pass `{"50256": -100}` to prevent the token from being generated.
+ As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated.
  logprobs: &completions_logprobs_configuration
  type: integer
  minimum: 0
@@ -2590,7 +2590,7 @@ components:
  nullable: true
  oneOf:
  - type: string
- default: 
+ default: <|endoftext|>
  example: "\n"
  nullable: true
  - type: array