mpt: utf-8 support, perplexity testing, repeat penalty sampling #184
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
ggerganov
reviewed
May 21, 2023
klosax
changed the title
klosax
changed the title
zenixls2
reviewed
May 22, 2023
| @@ -64,6 +64,105 @@ struct mpt_model { | |||
| std::map<std::string, struct ggml_tensor *> tensors; | |||
| }; | |||
|
|
|||
| struct mpt_params { | |||
There was a problem hiding this comment.
since this is in cpp, is it possible to extend the struct gpt_params?
zenixls2
reviewed
May 22, 2023
| } | ||
|
|
||
|
|
||
| std::vector<std::pair<double, gpt_vocab::id>> logits_id; |
There was a problem hiding this comment.
logit is float. Maybe use std::pair<float, gpt_vocab::id>?
|
also in llama.cpp/examples/main/main.cpp line 423 implements similar approach that makes use of the |
ggerganov
requested changes
May 22, 2023
examples/mpt/perplexity.cpp
Outdated
| ggml_free(model.ctx); | ||
|
|
||
| return 0; | ||
| } |
There was a problem hiding this comment.
No need to duplicate main.cpp in perplexity.cpp.
Just add a --perplexity CLI argument to main.cpp
Merged
klosax
changed the title
This was referenced May 23, 2023
ggerganov
approved these changes
May 24, 2023
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Outdated suggestions cannot be applied.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.
Follow up to pr #179 . Fixes issues #170 , #55 .
A better solution that will not affect the other examples that uses gpt_tokenize