mirror of
https://github.com/zenlm/gym.git
synced 2026-11-04 17:11:44 +00:00
## Major Changes - **Package Rename**: llamafactory → zoo-gym (PyPI) / gym (internal) - **Organization**: Rebranded to Zoo Labs Foundation Inc (501c3 non-profit) - **Complete Module Migration**: All src/llamafactory/ → src/gym/ - **Updated Metadata**: setup.py, pyproject.toml, README.md ## New Features - **Qwen3 Fine-tuning**: Full support with configs/qwen3_finetune.yaml - **Zen Nano Integration**: QLoRA config for 4B edge models - **Enhanced Documentation**: README-HF.md, QUICKSTART.md, LLM.md - **HuggingFace Integration**: .huggingface deployment config - **Training Scripts**: train_qwen3.py, train_qwen3_omni.py ## Technical Improvements - **Import Path Updates**: All internal references updated - **CLI Rename**: gym-cli command (backward compatible) - **Gradio WebUI**: Enhanced interface for training - **Educational Focus**: Democratizing AI education and research ## Testing - ✅ Package imports successfully - ✅ CLI functionality verified - ✅ Core dependencies resolved - 📋 CI tests pending ## Attribution Maintains original Apache 2.0 license with updated copyright to Zoo Labs Foundation Inc. All original LlamaFactory contributors acknowledged in commit history.
57 lines
1.8 KiB
Python
57 lines
1.8 KiB
Python
# Copyright 2025 the LlamaFactory team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import os
|
|
|
|
from gym.train.test_utils import load_dataset_module
|
|
|
|
|
|
DEMO_DATA = os.getenv("DEMO_DATA", "llamafactory/demo_data")
|
|
|
|
TINY_LLAMA3 = os.getenv("TINY_LLAMA3", "llamafactory/tiny-random-Llama-3")
|
|
|
|
TINY_DATA = os.getenv("TINY_DATA", "llamafactory/tiny-supervised-dataset")
|
|
|
|
TRAIN_ARGS = {
|
|
"model_name_or_path": TINY_LLAMA3,
|
|
"stage": "sft",
|
|
"do_train": True,
|
|
"finetuning_type": "full",
|
|
"template": "llama3",
|
|
"dataset": TINY_DATA,
|
|
"dataset_dir": "ONLINE",
|
|
"cutoff_len": 8192,
|
|
"output_dir": "dummy_dir",
|
|
"overwrite_output_dir": True,
|
|
"fp16": True,
|
|
}
|
|
|
|
|
|
def test_load_train_only():
|
|
dataset_module = load_dataset_module(**TRAIN_ARGS)
|
|
assert dataset_module.get("train_dataset") is not None
|
|
assert dataset_module.get("eval_dataset") is None
|
|
|
|
|
|
def test_load_val_size():
|
|
dataset_module = load_dataset_module(val_size=0.1, **TRAIN_ARGS)
|
|
assert dataset_module.get("train_dataset") is not None
|
|
assert dataset_module.get("eval_dataset") is not None
|
|
|
|
|
|
def test_load_eval_data():
|
|
dataset_module = load_dataset_module(eval_dataset=TINY_DATA, **TRAIN_ARGS)
|
|
assert dataset_module.get("train_dataset") is not None
|
|
assert dataset_module.get("eval_dataset") is not None
|