Implement v2.llama3 grammar sampling + some API request edge cases error handling #189
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ng code_interpreter tool in server_vllm
functionary/inference.py
Outdated
| )[0] | ||
| + prompt_template.fn_param_sep_token | ||
| ) | ||
| final_prompt += "all" + prompt_template.fn_param_sep_token |
There was a problem hiding this comment.
Should we create another abstract class for get_force_text_response_prefix() --> "" by default
and in template_v2, we will overwrite this by returning: "all\n". So in the future, if we change the template we don't have to if-else at this ?
| return ["<|start_header_id|>assistant<|end_header_id|>\n\n"] | ||
|
|
||
| def get_stop_tokens_for_generation(self) -> List[str]: | ||
| return ["<|eot_id|>", "<|end_of_text|>"] | ||
|
|
||
| def get_start_of_function_call_token(self) -> str: |
There was a problem hiding this comment.
I think we can remove this, right ?
There was a problem hiding this comment.
Oh, not sure why it was here. Removed
| @@ -312,3 +553,4 @@ def get_chat_template_jinja(self) -> str: | |||
|
|
|||
| def get_force_function_call_prefix(self, function_name: str): | |||
| return f"{self.function_separator}{function_name}\n" | |||
| return f"{self.function_separator}{function_name}\n" | |||
There was a problem hiding this comment.
Oh why made it repeated ?
There was a problem hiding this comment.
I think it was accidental. Removed
khai-meetkai
approved these changes
May 16, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
v2 FSM:
v2.llama3 FSM: