Llama2 handler #425
Closed
Llama2 handler #425
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
nik-mosaic
reviewed
Jul 30, 2023
|
|
||
| import deepspeed | ||
| import torch | ||
| from transformers import (AutoModelForCausalLM, AutoTokenizer, |
There was a problem hiding this comment.
I don't see AutoModel or AutoTokenizer used anywhere.
nik-mosaic
approved these changes
Jul 30, 2023
asfandyarq
approved these changes
Jul 31, 2023
|
|
||
| INPUT_KEY = 'input' | ||
| PARAMETERS_KEY = 'parameters' | ||
| MODEL_DTYPE = 'fp16' |
| def __init__( | ||
| self, | ||
| model_name_or_path: str, | ||
| ): |
There was a problem hiding this comment.
Could we add a max_output_tokens parameter here, or in the go server? We'd then clip user max_length values in requests to this.
This is a slow model and we'll probably need to limit it to globally to 128 tokens. Otherwise someone could send a super long request and tie up the entire server for >30 sec.
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Outdated suggestions cannot be applied.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.
No description provided.