Overhaul Conversation class and prompt templating (#25323)
* First commit while I figure this out * make fixup * Remove unused method * Store prompt attrib * Fix prompt argument for tests * Make same changes in fast tokenizer * Remove global prompts from fast tokenizer too * stash commit * stash commit * Migrate PromptConfig to its True Final Location * Replace Conversation entirely with the new class * Import/dependency fixes * Import/dependency fixes * Change format for lots of default prompts * More default prompt fixups * Revert llama old methods so we can compare * Fix some default configs * Fix some default configs * Fix misspelled kwarg * Fixes for Blenderbot * make fixup * little rebase cleanup * Add basic documentation * Quick doc fix * Truncate docstring for now * Add handling for the case when messages is a single string * Quick llama merges * Update conversational pipeline and tests * Add a couple of legacy properties for backward compatibility * More legacy handling * Add docstring for build_conversation_input_ids * Restructure PromptConfig * Let's start T E M P L A T I N G * Refactor all default configs to use templates instead * Revert changes to the special token properties since we don't need them anymore * More class templates * Make the sandbox even sandier * Everything replaced with pure templating * Remove docs for PromptConfig * Add testing and optional requirement boilerplate * Fix imports and make fixup * Fix LLaMA tests and add Conversation docstring * Finally get LLaMA working with the template system * Finally get LLaMA working with the template system * make fixup * make fixup * fmt-off for the long lists of test tokens * Rename method to apply_chat_template for now * Start on documentation * Make chat_template a property that reads through to the default if it's not set * Expand docs * Expand chat templating doc some more * trim/lstrip blocks by default and update doc * Few doc tweaks * rebase cleanup * Clarify docstring * rebase cleanup * rebase cleanup * make fixup * Quick doc edit * Reformat the standard template to match ChatML * Re-add PEFT check * Update docs/source/en/chat_templating.md Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Add apply_chat_template to the tokenizer doc * make fixup * Add doc links * Fix chat links * Fix chat links * Explain system messages in the doc * Add chat template test * Proper save-loading for chat template attribute * Add test skips for layout models * Remove _build_conversation_input_ids, add default_chat_template to code_llama * Make sure all LLaMA models are using the latest template * Remove default_system_prompt block in code_llama because it has no default prompt * Update ConversationPipeline preprocess * Add correct #Copied from links to the default_chat_templates * Remove unneeded type checking line * Add a dummy mark_processsed method * Reorganize Conversation to have **deprecated_kwargs * Update chat_templating.md * Quick fix to LLAMA tests * Small doc tweaks * Add proper docstrings and "copied from" statements to all default chat templates * Merge use_default_system_prompt support for code_llama too * Improve clarity around self.chat_template * Docstring fix * Fix blenderbot default template * More doctest fix * Break out some tokenizer kwargs * Update doc to explain default templates * Quick tweaks to tokenizer args * Cleanups for tokenizer args * Add note about cacheing * Quick tweak to the chat-templating doc * Update the LLaMA template with error checking and correct system message embedding * make fixup * make fixup * add requires_jinja * Cleanup to expected output formatting * Add cacheing * Fix typo in llama default template * Update LLaMA tests * Update documentation * Improved legacy handling in the Conversation class * Update Jinja template with proper error handling * Quick bugfix * Proper exception raising * Change cacheing behaviour so it doesn't try to pickle an entire Jinja env * make fixup * rebase cleanup --------- Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
This commit is contained in:
Matt
@@ -32,6 +32,7 @@ from transformers.convert_slow_tokenizer import convert_slow_tokenizer
|
||||
from transformers.testing_utils import (
|
||||
get_tests_dir,
|
||||
nested_simplify,
|
||||
require_jinja,
|
||||
require_sentencepiece,
|
||||
require_tokenizers,
|
||||
require_torch,
|
||||
@@ -574,6 +575,32 @@ class LlamaIntegrationTest(unittest.TestCase):
|
||||
# a dummy prefix space is not added by the sp_model as it was de-activated
|
||||
self.assertEqual(tokens, tokenizer.sp_model.encode("▁▁▁", out_type=str))
|
||||
|
||||
@require_jinja
|
||||
def test_tokenization_for_chat(self):
|
||||
tokenizer = LlamaTokenizer.from_pretrained("huggyllama/llama-7b", legacy=False)
|
||||
|
||||
test_chats = [
|
||||
[{"role": "system", "content": "You are a helpful chatbot."}, {"role": "user", "content": "Hello!"}],
|
||||
[
|
||||
{"role": "system", "content": "You are a helpful chatbot."},
|
||||
{"role": "user", "content": "Hello!"},
|
||||
{"role": "assistant", "content": "Nice to meet you."},
|
||||
],
|
||||
[{"role": "user", "content": "Hello!"}],
|
||||
]
|
||||
# Matt: The third test case tests the default system message, but if this is ever changed in the
|
||||
# class/repo code then that test will fail, and the case will need to be updated.
|
||||
tokenized_chats = [tokenizer.apply_chat_template(test_chat) for test_chat in test_chats]
|
||||
# fmt: off
|
||||
expected_tokens = [
|
||||
[1, 29961, 25580, 29962, 3532, 14816, 29903, 6778, 13, 3492, 526, 263, 8444, 13563, 7451, 29889, 13, 29966, 829, 14816, 29903, 6778, 13, 13, 10994, 29991, 518, 29914, 25580, 29962],
|
||||
[1, 29961, 25580, 29962, 3532, 14816, 29903, 6778, 13, 3492, 526, 263, 8444, 13563, 7451, 29889, 13, 29966, 829, 14816, 29903, 6778, 13, 13, 10994, 29991, 518, 29914, 25580, 29962, 20103, 304, 5870, 366, 29889, 29871, 2],
|
||||
[1, 29961, 25580, 29962, 3532, 14816, 29903, 6778, 13, 3492, 526, 263, 8444, 29892, 3390, 1319, 322, 15993, 20255, 29889, 29849, 1234, 408, 1371, 3730, 408, 1950, 29892, 1550, 1641, 9109, 29889, 3575, 6089, 881, 451, 3160, 738, 10311, 1319, 29892, 443, 621, 936, 29892, 11021, 391, 29892, 7916, 391, 29892, 304, 27375, 29892, 18215, 29892, 470, 27302, 2793, 29889, 3529, 9801, 393, 596, 20890, 526, 5374, 635, 443, 5365, 1463, 322, 6374, 297, 5469, 29889, 13, 13, 3644, 263, 1139, 947, 451, 1207, 738, 4060, 29892, 470, 338, 451, 2114, 1474, 16165, 261, 296, 29892, 5649, 2020, 2012, 310, 22862, 1554, 451, 1959, 29889, 960, 366, 1016, 29915, 29873, 1073, 278, 1234, 304, 263, 1139, 29892, 3113, 1016, 29915, 29873, 6232, 2089, 2472, 29889, 13, 29966, 829, 14816, 29903, 6778, 13, 13, 10994, 29991, 518, 29914, 25580, 29962]
|
||||
]
|
||||
# fmt: on
|
||||
for tokenized_chat, expected_tokens in zip(tokenized_chats, expected_tokens):
|
||||
self.assertListEqual(tokenized_chat, expected_tokens)
|
||||
|
||||
|
||||
@require_sentencepiece
|
||||
@require_tokenizers
|
||||
|
||||
Reference in New Issue
Block a user