Modify benchmarks #563
Merged
Modify benchmarks #563
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
dacorvo
force-pushed
the
modify-benchmarks
branch
from
280f41c
to
7875e94
Compare
michaelbenayoun
approved these changes
Apr 12, 2024
Comment on lines
31
to
32
| def get_input_ids(tokens, batch_size, input_length): | ||
| return tokens.input_ids[:, :input_length].repeat((batch_size, 1)) |
There was a problem hiding this comment.
nit: if tokens.input_ids initially has a batch size > 1 the output will have a batch size of batch_size x original_batch_size, maybe just select the first batch before the repeat.
Comment on lines
23
to
39
|
|
||
| for model_name, model_configuration in model_configurations.items(): | ||
| model_id, batch_size, seq_length = model_configuration | ||
| model = NeuronModelForCausalLM.from_pretrained( | ||
| model_id, | ||
| export=True, | ||
| batch_size=batch_size, | ||
| sequence_length=seq_length, | ||
| auto_cast_type="bf16", | ||
| num_cores=NUM_CORES, | ||
| ) | ||
| with TemporaryDirectory() as tmpdir: | ||
| model.save_pretrained(tmpdir) | ||
| tokenizer = AutoTokenizer.from_pretrained(model_id) | ||
| tokenizer.save_pretrained(tmpdir) | ||
| json_path = f"{model_name}.json" | ||
| run(tmpdir, 256, 2048, json_path=json_path) |
There was a problem hiding this comment.
Maybe add if __name__ == "__main__" to not run this code at any import.
Comment on lines
+22
to
+23
| with open("./wiki.txt") as f: | ||
| prompt = f.read() |
There was a problem hiding this comment.
You read a 12k lines document and you tokenize everything at once?
There was a problem hiding this comment.
yes, tokenizer is a brute
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.
What does this PR do?
Modify LLM benchmarks section: