add save_load_state example #1150
Merged
Conversation
This file contains hidden or 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
approved these changes
Apr 24, 2023
| @@ -0,0 +1,133 @@ | |||
| #include <vector> | |||
| #include <iostream> | |||
There was a problem hiding this comment.
Suggested change
| #include <iostream> | |
| #include <cstdio> |
Is better
| auto n_prompt_tokens = llama_tokenize(ctx, params.prompt.c_str(), tokens.data(), tokens.size(), true); | ||
|
|
||
| if (n_prompt_tokens < 1) { | ||
| cout << "Failed to tokenize prompt" << endl; |
There was a problem hiding this comment.
Suggested change
| cout << "Failed to tokenize prompt" << endl; | |
| fprintf(stderr, "%s : failed to tokenize prompt\n", __func__); |
etc.
|
I changed cout to printf / fprintf in this last commit. |
|
Sorry, one more thing - all filenames use dashes
|
|
Sure, I changed it :) |
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Outdated suggestions cannot be applied.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.
This is the save_load_state example script from #730 (comment)
It will load model params read from command line.
Then evaluate and print the initial prompt and save the state.
n_predict tokens are generate and printed.
Model is freed and load in new context.
Load the state and generate and print n_predict.
The n_predict generated tokens should be the same.