Feature/top p sampling #1360
Merged
Feature/top p sampling #1360
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
rasbt
reviewed
Apr 25, 2024
carmocca
reviewed
Apr 25, 2024
rasbt
reviewed
Apr 26, 2024
rasbt
reviewed
Apr 26, 2024
carmocca
reviewed
Apr 29, 2024
rasbt
reviewed
May 2, 2024
rasbt
reviewed
May 2, 2024
|
Thanks for all the updates and fixes. It looks all great to me now. |
rasbt
approved these changes
May 2, 2024
Thank you @rasbt: i had missed your comment |
|
No worries at all, I also thought it was probably quicker to just add instead of explain 😅 |
carmocca
reviewed
May 6, 2024
Comment on lines
+115
to
+127
| def test_generate_different_results_with_different_top_p(): | ||
| config = Config(block_size=128, vocab_size=16, n_layer=1, n_head=4, n_embd=8) | ||
| model = GPT(config) | ||
| model.max_seq_length = 50 | ||
| model.set_kv_cache(batch_size=1) | ||
|
|
||
| torch.manual_seed(123) | ||
| input_idx = torch.randint(10, size=(1,)) | ||
|
|
||
| output1 = generate.generate(model, input_idx, 20, top_p=1.0) | ||
| output2 = generate.generate(model, input_idx, 20, top_p=0.1) | ||
|
|
||
| assert not torch.equal(output1, output2) |
There was a problem hiding this comment.
This test is not useful because it will also pass if you set the same top_p. That's because multinomial advances the rng state.
For it to achieve the intended result, you need to seed before each call
torch.manual_seed(123)
input_idx = torch.randint(10, size=(1,))
torch.manual_seed(123)
output1 = generate.generate(model, input_idx, 20, top_p=1.0)
torch.manual_seed(123)
output2 = generate.generate(model, input_idx, 20, top_p=0.1)cc @rasbt
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Outdated suggestions cannot be applied.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 PR adds the nucleus-sampling (aka top-p sampling) as specified from https://arxiv.org/abs/1904.09751.
In top-p sampling the next token is chosen from the smallest set of tokens with a cumulative probability greater than
top-p, i.e. by selecting the highest probability tokens whose cumulative probability exceeds thetop-pthreshold.