mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
e830814399
* Add distribution CLI scaffolding * More progress towards `llama distribution install` * getting closer to a distro definition, distro install + configure works * Distribution server now functioning * read existing configuration, save enums properly * Remove inference uvicorn server entrypoint and llama inference CLI command * updated dependency and client model name * Improved exception handling * local imports for faster cli * undo a typo, add a passthrough distribution * implement full-passthrough in the server * add safety adapters, configuration handling, server + clients * cleanup, moving stuff to common, nuke utils * Add a Path() wrapper at the earliest place * fixes * Bring agentic system api to toolchain Add adapter dependencies and resolve adapters using a topological sort * refactor to reduce size of `agentic_system` * move straggler files and fix some important existing bugs * ApiSurface -> Api * refactor a method out * Adapter -> Provider * Make each inference provider into its own subdirectory * installation fixes * Rename Distribution -> DistributionSpec, simplify RemoteProviders * dict key instead of attr * update inference config to take model and not model_dir * Fix passthrough streaming, send headers properly not part of body :facepalm * update safety to use model sku ids and not model dirs * Update cli_reference.md * minor fixes * add DistributionConfig, fix a bug in model download * Make install + start scripts do proper configuration automatically * Update CLI_reference * Nuke fp8_requirements, fold fbgemm into common requirements * Update README, add newline between API surface configurations * Refactor download functionality out of the Command so can be reused * Add `llama model download` alias for `llama download` * Show message about checksum file so users can check themselves * Simpler intro statements * get ollama working * Reduce a bunch of dependencies from toolchain Some improvements to the distribution install script * Avoid using `conda run` since it buffers everything * update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes * add validation for configuration input * resort imports * make optional subclasses default to yes for configuration * Remove additional_pip_packages; move deps to providers * for inline make 8b model the default * Add scripts to MANIFEST * allow installing from test.pypi.org * Fix #2 to help with testing packages * Must install llama-models at that same version first * fix PIP_ARGS --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Hardik Shah <hjshah@meta.com>
128 lines
3.4 KiB
Python
128 lines
3.4 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from datetime import datetime
|
|
|
|
from typing import Any, Dict, List, Optional, Protocol
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_models.llama3_1.api.datatypes import * # noqa: F403
|
|
from llama_toolchain.dataset.api.datatypes import * # noqa: F403
|
|
from llama_toolchain.common.training_types import * # noqa: F403
|
|
from .datatypes import * # noqa: F403
|
|
|
|
|
|
@json_schema_type
|
|
class PostTrainingSFTRequest(BaseModel):
|
|
"""Request to finetune a model."""
|
|
|
|
job_uuid: str
|
|
|
|
model: str
|
|
dataset: TrainEvalDataset
|
|
validation_dataset: TrainEvalDataset
|
|
|
|
algorithm: FinetuningAlgorithm
|
|
algorithm_config: Union[
|
|
LoraFinetuningConfig, QLoraFinetuningConfig, DoraFinetuningConfig
|
|
]
|
|
|
|
optimizer_config: OptimizerConfig
|
|
training_config: TrainingConfig
|
|
|
|
# TODO: define these
|
|
hyperparam_search_config: Dict[str, Any]
|
|
logger_config: Dict[str, Any]
|
|
|
|
|
|
@json_schema_type
|
|
class PostTrainingRLHFRequest(BaseModel):
|
|
"""Request to finetune a model."""
|
|
|
|
job_uuid: str
|
|
|
|
finetuned_model: URL
|
|
|
|
dataset: TrainEvalDataset
|
|
validation_dataset: TrainEvalDataset
|
|
|
|
algorithm: RLHFAlgorithm
|
|
algorithm_config: Union[DPOAlignmentConfig]
|
|
|
|
optimizer_config: OptimizerConfig
|
|
training_config: TrainingConfig
|
|
|
|
# TODO: define these
|
|
hyperparam_search_config: Dict[str, Any]
|
|
logger_config: Dict[str, Any]
|
|
|
|
|
|
class PostTrainingJob(BaseModel):
|
|
|
|
job_uuid: str
|
|
|
|
|
|
@json_schema_type
|
|
class PostTrainingJobStatusResponse(BaseModel):
|
|
"""Status of a finetuning job."""
|
|
|
|
job_uuid: str
|
|
status: PostTrainingJobStatus
|
|
|
|
scheduled_at: Optional[datetime] = None
|
|
started_at: Optional[datetime] = None
|
|
completed_at: Optional[datetime] = None
|
|
|
|
resources_allocated: Optional[Dict[str, Any]] = None
|
|
|
|
checkpoints: List[Checkpoint] = Field(default_factory=list)
|
|
|
|
|
|
@json_schema_type
|
|
class PostTrainingJobArtifactsResponse(BaseModel):
|
|
"""Artifacts of a finetuning job."""
|
|
|
|
job_uuid: str
|
|
checkpoints: List[Checkpoint] = Field(default_factory=list)
|
|
|
|
# TODO(ashwin): metrics, evals
|
|
|
|
|
|
class PostTraining(Protocol):
|
|
@webmethod(route="/post_training/supervised_fine_tune")
|
|
def post_supervised_fine_tune(
|
|
self,
|
|
request: PostTrainingSFTRequest,
|
|
) -> PostTrainingJob: ...
|
|
|
|
@webmethod(route="/post_training/preference_optimize")
|
|
def post_preference_optimize(
|
|
self,
|
|
request: PostTrainingRLHFRequest,
|
|
) -> PostTrainingJob: ...
|
|
|
|
@webmethod(route="/post_training/jobs")
|
|
def get_training_jobs(self) -> List[PostTrainingJob]: ...
|
|
|
|
# sends SSE stream of logs
|
|
@webmethod(route="/post_training/job/logs")
|
|
def get_training_job_logstream(self, job_uuid: str) -> PostTrainingJobLogStream: ...
|
|
|
|
@webmethod(route="/post_training/job/status")
|
|
def get_training_job_status(
|
|
self, job_uuid: str
|
|
) -> PostTrainingJobStatusResponse: ...
|
|
|
|
@webmethod(route="/post_training/job/cancel")
|
|
def cancel_training_job(self, job_uuid: str) -> None: ...
|
|
|
|
@webmethod(route="/post_training/job/artifacts")
|
|
def get_training_job_artifacts(
|
|
self, job_uuid: str
|
|
) -> PostTrainingJobArtifactsResponse: ...
|