forked from phoenix-oss/llama-stack-mirror
abdf7cddf3
* wip * dataset validation * test_scoring * cleanup * clean up test * comments * error checking * dataset client * test client: * datasetio client * clean up * basic scoring function works * scorer wip * equality scorer * score batch impl * score batch * update scoring test * refactor * validate scorer input * address comments * evals with generation * add all rows scores to ScoringResult * minor typing * bugfix * scoring function def rename * rebase name * refactor * address comments * Update iOS inference instructions for new quantization * Small updates to quantization config * Fix score threshold in faiss * Bump version to 0.0.45 * Handle both ipv6 and ipv4 interfaces together * update manifest for build templates * Update getting_started.md * chatcompletion & completion input type validation * inclusion->subsetof * error checking * scoring_function -> scoring_fn rename, scorer -> scoring_fn rename * address comments * [Evals API][5/n] fixes to generate openapi spec (#323) * generate openapi * typing comment, dataset -> dataset_id * remove custom type * sample eval run.yaml --------- Co-authored-by: Dalton Flanagan <6599399+dltn@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
53 lines
1.5 KiB
Python
53 lines
1.5 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 enum import Enum
|
|
|
|
from typing import Any, Dict, List, Optional, Protocol
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_models.llama3.api.datatypes import * # noqa: F403
|
|
|
|
|
|
class FilteringFunction(Enum):
|
|
"""The type of filtering function."""
|
|
|
|
none = "none"
|
|
random = "random"
|
|
top_k = "top_k"
|
|
top_p = "top_p"
|
|
top_k_top_p = "top_k_top_p"
|
|
sigmoid = "sigmoid"
|
|
|
|
|
|
@json_schema_type
|
|
class SyntheticDataGenerationRequest(BaseModel):
|
|
"""Request to generate synthetic data. A small batch of prompts and a filtering function"""
|
|
|
|
dialogs: List[Message]
|
|
filtering_function: FilteringFunction = FilteringFunction.none
|
|
model: Optional[str] = None
|
|
|
|
|
|
@json_schema_type
|
|
class SyntheticDataGenerationResponse(BaseModel):
|
|
"""Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."""
|
|
|
|
synthetic_data: List[Dict[str, Any]]
|
|
statistics: Optional[Dict[str, Any]] = None
|
|
|
|
|
|
class SyntheticDataGeneration(Protocol):
|
|
@webmethod(route="/synthetic_data_generation/generate")
|
|
def synthetic_data_generate(
|
|
self,
|
|
dialogs: List[Message],
|
|
filtering_function: FilteringFunction = FilteringFunction.none,
|
|
model: Optional[str] = None,
|
|
) -> Union[SyntheticDataGenerationResponse]: ...
|