mostlyai-engine 1.4.3__tar.gz → 1.4.4__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/PKG-INFO +1 -1
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/__init__.py +1 -1
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/training.py +5 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/pyproject.toml +2 -1
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/.gitignore +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/LICENSE +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/README.md +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_common.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_dtypes.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/__init__.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/__init__.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/categorical.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/datetime.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/numeric.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/text.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/__init__.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/categorical.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/character.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/datetime.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/itt.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/lat_long.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/numeric.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/__init__.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/common.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/encoding.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/__init__.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/base.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/hf_engine.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/vllm_engine.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/generation.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/lstm.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/tokenizer_utils.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/xgrammar_utils.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_memory.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/__init__.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/argn.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/common.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/encoding.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/fairness.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/generation.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_tabular/training.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_training_utils.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_workspace.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/analysis.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/domain.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/encoding.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/generation.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/logging.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/random_state.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/splitting.py +0 -0
- {mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/training.py +0 -0
|
@@ -22,7 +22,7 @@ from mostlyai.engine.splitting import split
|
|
|
22
22
|
from mostlyai.engine.training import train
|
|
23
23
|
|
|
24
24
|
__all__ = ["split", "analyze", "encode", "train", "generate", "init_logging", "set_random_state"]
|
|
25
|
-
__version__ = "1.4.
|
|
25
|
+
__version__ = "1.4.4"
|
|
26
26
|
|
|
27
27
|
# suppress specific warning related to os.fork() in multi-threaded processes
|
|
28
28
|
warnings.filterwarnings("ignore", category=DeprecationWarning, message=".*multi-threaded.*fork.*")
|
|
@@ -16,6 +16,7 @@ import gc
|
|
|
16
16
|
import json
|
|
17
17
|
import logging
|
|
18
18
|
import math
|
|
19
|
+
import os
|
|
19
20
|
import time
|
|
20
21
|
import warnings
|
|
21
22
|
from collections.abc import Callable
|
|
@@ -431,6 +432,10 @@ def train(
|
|
|
431
432
|
model_config = LSTMFromScratchConfig(vocab_size=len(tokenizer), with_dp=with_dp)
|
|
432
433
|
model = LSTMFromScratchLMHeadModel(model_config).to(device)
|
|
433
434
|
else:
|
|
435
|
+
# use MOSTLY_HUGGING_FACE_TOKEN if available
|
|
436
|
+
if os.getenv("MOSTLY_HUGGING_FACE_TOKEN"):
|
|
437
|
+
os.environ["HF_TOKEN"] = os.environ["MOSTLY_HUGGING_FACE_TOKEN"]
|
|
438
|
+
|
|
434
439
|
model, model_config = load_base_model_and_config(
|
|
435
440
|
model_id_or_path,
|
|
436
441
|
device=device,
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "mostlyai-engine"
|
|
3
|
-
version = "1.4.
|
|
3
|
+
version = "1.4.4"
|
|
4
4
|
description = "Synthetic Data Engine"
|
|
5
5
|
authors = [{ name = "MOSTLY AI", email = "dev@mostly.ai" }]
|
|
6
6
|
requires-python = ">=3.10"
|
|
@@ -64,6 +64,7 @@ docs = [
|
|
|
64
64
|
"mkdocs>=1.6",
|
|
65
65
|
"mkdocstrings[crystal, python]>=0.29",
|
|
66
66
|
"mkdocs-material>=9.0",
|
|
67
|
+
"mkdocs-llmstxt>=0.2",
|
|
67
68
|
"griffe>=1.0",
|
|
68
69
|
"pymdown-extensions>=10.0",
|
|
69
70
|
"griffe-fieldz>=0.2",
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/datetime.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/numeric.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/language/text.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/character.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/datetime.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/itt.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/lat_long.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_encoding_types/tabular/numeric.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/hf_engine.py
RENAMED
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/engine/vllm_engine.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{mostlyai_engine-1.4.3 → mostlyai_engine-1.4.4}/mostlyai/engine/_language/tokenizer_utils.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|