tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

feat: add config for optional parameters in a chat message (#2260)

Browse Source 
* feat: add config for optional parameters in a chat message

* chore: cleanup

* chore: fix nits and add light docs

* docs: update docs/dataset-formats/conversation.qmd

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>

* feat: configurable message mappings, jinja template analyzer

* chore: handle bradley terry

* docs: update docs

* refactor: change order of mappings, improve message transform

* refactor: make chat awware of property mappings

* chore: remove .python-version

* chore: revert change

* chore: add dataset validation to tests where appropriate

* chore: add dataset validation to tests where appropriate

* chore: clean up handling of ds_cfg

* chore: recursively serialize config

* make sure to use the return value from validate_config

* DefaultDict pickle/unpickle fix

* fix super call for override

* refactor: message fields

* chore: empty commit

* tests: validate config before using

* chore: add config validation to all e2e tests

* chore: add unneeded logging

* chore: add missed config validation

* chore: pass field_messages to prompter

* test: fix borked test

* chore: remove uninteded file

* chore: add deprecation warning and update chat_datasets script

* chore: lint

* refactor: message fields

* feat: update axolotlinputconfig and test_models

- add configdict import in axolotl/utils/config/models/input/v0_4_1/__init__.py
- remove unnecessary line breaks in sftdataset, dpodataset, ktodataset, stepwisesuperviseddataset classes
- update model_dump method in axolotlinputconfig to exclude none values
- correct typo in test_models.py comment

* feat: simplify dpodataset and ktodataset classes in config models

removed several optional fields from dpodataset and ktodataset classes in axolotl/utils/config/models/input/v0_4_1. this simplifies the configuration subsets for these datasets.

* feat: improve readability and structure in dataset configuration models

this commit enhances the readability and structure of the dataset configuration models in the `axolotl/utils/config/models/input/v0_4_1` module. it removes unused `configdict` import and adds line breaks to separate class definitions for better clarity. additionally, a minor documentation fix is included to ensure a newline at the end of the `stepwise_supervised.qmd` file.

* feat: change log level from info to debug in chattemplatestrategy

* feat(prompt_strategies): refactor chattemplateprompter and chattemplatestrategy

- Make `chat_template` a required parameter in `ChatTemplatePrompter` constructor
- Add default value for `message_property_mappings` in `ChatTemplatePrompter` constructor
- Add `messages_array_name` property to `ChatTemplatePrompter`
- Change `processor` type to Optional in `ChatTemplatePrompter`
- Add TypeError check for `processor` in `ChatTemplatePrompter.build_prompt`
- Remove `_messages` property from `ChatTemplateStrategy`
- Make `prompter` a required parameter and add type hint in `ChatTemplateStrategy` constructor
- Remove `messages` getter and setter from `ChatTemplateStrategy`
- Use `prompter.messages_array_name` in `ChatTemplateStrategy.get_conversation_thread`
- Remove condition to set `messages` field in `load` function

* feat(tests/utils): ignore type check in load_model call in test_models.py

* feat: improve type handling and test structure in chat templates

- Add return type hint for `get_chat_template` function in `chat_templates.py`
- Remove unnecessary assignment of `strategy.messages` in several test cases
- Add `messages_array_name` parameter to various test configurations in `test_chat_templates.py` and `test_chat_templates_advanced.py`
- Remove redundant `strategy.messages` assignment in `test_chat_templates_advanced.py`

* feat(axolotl): enhance chat strategy with datasetconfig support

This commit introduces support for DatasetConfig in the ChatTemplateStrategy. It also refines the strategy loader to handle different types of ds_cfg inputs and improves the clarity of the code by formatting and reordering. The key changes include:

- Importing Union from typing and BaseModel from pydantic.
- Adding DatasetConfig as an optional type for ds_cfg in StrategyLoader.
- Adjusting the handling of ds_cfg in StrategyLoader to account for BaseModel instances.
- Refactoring the prompter_params and strategy_params for better readability.
- Changing the reference from prompt[self.messages] to prompt[self.prompter.messages_array_name] in the is_prompt_batched method.

* feat: update message handling in btchattemplatestrategy

* Replace `self.messages` with direct string references to "chosen_messages" and "rejected_messages"
* Append system, user, and assistant content directly to "chosen_messages" and "rejected_messages"
* Add a new attribute "messages_array_name" to the `load` function parameters
* Remove the conditional attribute assignment for "field_messages" in the `load` function

* feat: add config validation in test_kd.py

- Import `validate_config` from `axolotl.utils.config`
- Validate the configuration in `test_llama_kd` and another function in `TestKnowledgeDistillation` class

* feat: enhance config validation and capabilities handling

* Import `EnvCapabilities` and `GPUCapabilities` from `axolotl.utils.config.models.internals`
* Update `validate_config` function to create `KTODataset` and `SFTDataset` instances using `dict(ds_cfg)`
* Replace `capabilities` and `env_capabilities` with instances of `GPUCapabilities` and `EnvCapabilities` respectively in `AxolotlConfigWCapabilities` model dump

* feat: update config validation in axolotl utils

- Remove import of `EnvCapabilities` and `GPUCapabilities` from `axolotl.utils.config.models.internals`
- Update `validate_config` function to use `capabilities` and `env_capabilities` directly instead of creating new instances of `GPUCapabilities` and `EnvCapabilities`

* feat: refactor strategyloader in chat_template.py

- Extracted the creation of strategy parameters into a separate function, `_get_strategy_params(cfg, dataset_config)`
- Created a new function, `_get_strategy_cls()`, to obtain the strategy class
- Replaced `ChatTemplateStrategy` with `strategy_cls` for strategy instantiation

* trigger CI

* chore: revert dataset config changes for kto/dpo

* subject: refactor: rename 'messages_array_name' to 'field_messages'

Body:
- Renamed 'messages_array_name' to 'field_messages' in 'ChatTemplatePrompter' class and its usages in 'chat_template.py'
- Updated 'load' function in 'bradley_terry/chat_template.py' to reflect the change
- Adjusted 'get_chat_template_msg_variables' and 'get_message_vars' methods in 'jinja_template_analyzer.py' to use the new variable name
- Modified 'StrategyLoader' in 'chat_template.py' to use 'field_messages'
- Updated tests in 'test_chat_templates.py' and 'test_chat_templates_advanced.py' to use 'field_messages' instead of 'messages_array_name'

* feat: refactor prompt strategies and update config models

* Remove redundant 'return None' in `axolotl/prompt_strategies/__init__.py`
* Simplify message handling in `axolotl/prompt_strategies/bradley_terry/chat_template.py` by using a single 'messages' list instead of separate 'chosen_messages' and 'rejected_messages' lists
* Update default 'message_property_mappings' in `axolotl/prompt_strategies/bradley_terry/chat_template.py`
* Add 'field_messages' field to `axolotl/utils/config/models/input/v0_4_1/__init__.py` configuration model

* chore: remove unused input

* chore: remove redundant type ignore

* fix: remove old configs and update examples

* fix: type check

* fix: remove loading old config in ChatMessage

* fix: update faq with potential new undefinederror

* fix: add debug if property mapped is not found

* chore: improve explanation for unmapped properties

* fix: update docs with new config

* chore: add note for deprecation config and del old config from dict

---------

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
Co-authored-by: Wing Lian <wing@axolotl.ai>
Co-authored-by: NanoCode012 <nano@axolotl.ai>
This commit is contained in:
NJordan72
2025-02-17 21:59:27 -05:00
committed by GitHub
parent 3aac3b1da9
commit b194e17c28
51 changed files with 1190 additions and 230 deletions
Download Patch File Download Diff File Expand all files Collapse all files

131
tests/prompt_strategies/test_chat_templates_advanced.py
View File

@@ -3,7 +3,6 @@ tests for chat_template prompt strategy
"""
import logging
import unittest
from copy import deepcopy
import pytest
@@ -123,15 +122,15 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=True,
sequence_len=512,
roles_to_train=["assistant"],
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
turns = strategy.get_conversation_thread(basic_dataset[0])
labels = res["labels"]
@@ -180,15 +179,15 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
sequence_len=512,
roles_to_train=["assistant"],
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
turns = strategy.get_conversation_thread(basic_dataset[0])
labels = res["labels"]
@@ -241,20 +240,15 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
sequence_len=512,
roles_to_train=["assistant", "human"],
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
labels = res["labels"]
input_ids = res["input_ids"]
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
turns = strategy.get_conversation_thread(basic_dataset[0])
labels = res["labels"]
@@ -307,15 +301,15 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=True,
sequence_len=512,
roles_to_train=["human", "assistant"],
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
turns = strategy.get_conversation_thread(basic_dataset[0])
labels = res["labels"]
@@ -360,8 +354,8 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -369,7 +363,7 @@ class TestChatTemplateConfigurations:
roles_to_train=[],
train_on_eos="none", # Add this line
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
labels = res["labels"]
@@ -400,8 +394,8 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -409,7 +403,7 @@ class TestChatTemplateConfigurations:
roles_to_train=["assistant"],
train_on_eos="all",
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
labels = res["labels"]
input_ids = res["input_ids"]
@@ -446,8 +440,8 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -455,7 +449,6 @@ class TestChatTemplateConfigurations:
roles_to_train=["assistant"],
train_on_eos="turn",
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
turns = strategy.get_conversation_thread(basic_dataset[0])
labels = res["labels"]
@@ -526,8 +519,8 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -535,7 +528,7 @@ class TestChatTemplateConfigurations:
roles_to_train=["assistant"],
train_on_eos="last",
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
labels = res["labels"]
input_ids = res["input_ids"]
@@ -578,8 +571,8 @@ class TestChatTemplateConfigurations:
chat_template=get_chat_template(
chat_template, jinja_template=chat_template_jinja
),
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -587,7 +580,7 @@ class TestChatTemplateConfigurations:
roles_to_train=["assistant"],
train_on_eos="none",
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
labels = res["labels"]
input_ids = res["input_ids"]
@@ -624,15 +617,15 @@ class TestChatTemplateConfigurations:
chat_template, jinja_template=chat_template_jinja
),
drop_system_message=True,
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
field_messages="conversations",
),
tokenizer=tokenizer,
train_on_inputs=False,
sequence_len=512,
roles_to_train=["assistant"],
)
strategy.messages = "conversations"
res = strategy.tokenize_prompt(basic_dataset[0])
input_ids = res["input_ids"]
@@ -668,8 +661,7 @@ class TestChatTemplateConfigurations:
chat_template, jinja_template=chat_template_jinja
),
roles=custom_roles,
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -741,8 +733,7 @@ class TestChatTemplateConfigurations:
),
message_field_training="train",
message_field_training_detail="train_detail",
message_field_role="from",
message_field_content="value",
message_property_mappings={"role": "from", "content": "value"},
),
tokenizer=tokenizer,
train_on_inputs=False,
@@ -911,6 +902,64 @@ class TestChatTemplateConfigurations:
LOG.debug(f"Final labels: {labels}")
LOG.debug(f"Final input_ids: {input_ids}")
def test_get_chat_template_variables(
self, tokenizer, chat_template, chat_template_jinja, eos_token, request
):
LOG.info("Testing get_chat_template_variables")
if __name__ == "__main__":
unittest.main()
actual_tokenizer, actual_jinja_template = self.setup_tokenizer(
tokenizer, chat_template, chat_template_jinja, eos_token, request
)
prompter = ChatTemplatePrompter(
actual_tokenizer,
chat_template=get_chat_template(
chat_template, jinja_template=actual_jinja_template
),
message_property_mappings={"from": "role", "value": "content"},
)
variables = prompter.get_chat_template_msg_variables(
actual_jinja_template
if actual_jinja_template
else actual_tokenizer.get_chat_template(),
"messages",
)
if chat_template == "llama3":
assert variables == {"role", "content"}, (
f"Expected variables: {'role', 'content'} from {tokenizer}/{chat_template}\n"
f"Got: {variables}\n"
f"Chat template: {actual_jinja_template}"
)
elif chat_template == "chatml":
assert variables == {"role", "content"}, (
f"Expected variables: {'role', 'content'} from {tokenizer}/{chat_template}\n"
f"Got: {variables}\n"
f"Chat template: {actual_jinja_template}"
)
elif chat_template == "jinja" and tokenizer == "mistralv03_tokenizer":
assert variables == {"role", "content", "tool_call_id", "tool_calls"}, (
f"Expected variables: {'role', 'content', 'tool_call_id', 'tool_calls'} from {tokenizer}/{chat_template}\n"
f"Got: {variables}\n"
f"Chat template: {actual_jinja_template}"
)
elif chat_template == "jinja" and tokenizer == "gemma2_tokenizer":
assert variables == {"role", "content"}, (
f"Expected variables: {'role', 'content'} from {tokenizer}/{chat_template}\n"
f"Got: {variables}\n"
f"Chat template: {actual_jinja_template}"
)
elif chat_template == "phi_35":
assert variables == {"role", "content"}, (
f"Expected variables: {'role', 'content'} from {tokenizer}/{chat_template}\n"
f"Got: {variables}\n"
f"Chat template: {actual_jinja_template}"
)
else:
LOG.warning(
f"Unsupported chat template: {chat_template} with {chat_template_jinja}"
)
raise ValueError(
f"Unsupported chat template: {chat_template} with {chat_template_jinja}"
)