423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 18:20:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[deps] goodbye python 3.9 (#9677)

Browse Source 
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: hiyouga <16256802+hiyouga@users.noreply.github.com>
Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
This commit is contained in:
Copilot
2025-12-27 02:50:44 +08:00
committed by GitHub
parent b44f651e09
commit eceec8ab69
48 changed files with 267 additions and 284 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
scripts/megatron_merge.py
View File

@@ -16,7 +16,6 @@
# limitations under the License.
import os
from typing import Optional
import fire
import torch
@@ -34,7 +33,7 @@ def convert_mca_to_hf(
output_path: str = "./output",
bf16: bool = False,
fp16: bool = False,
convert_model_max_length: Optional[int] = None,
convert_model_max_length: int | None = None,
):
"""Convert megatron checkpoint to HuggingFace format.
@@ -67,11 +66,11 @@ def convert(
output_path: str = "./output",
bf16: bool = False,
fp16: bool = False,
convert_model_max_length: Optional[int] = None,
convert_model_max_length: int | None = None,
tensor_model_parallel_size: int = 1,
pipeline_model_parallel_size: int = 1,
expert_model_parallel_size: int = 1,
virtual_pipeline_model_parallel_size: Optional[int] = None,
virtual_pipeline_model_parallel_size: int | None = None,
):
"""Convert checkpoint between MCA and HuggingFace formats.

4
scripts/stat_utils/cal_ppl.py
View File

@@ -14,7 +14,7 @@
import json
from dataclasses import dataclass
from typing import Any, Literal, Optional
from typing import Any, Literal
import fire
import torch
@@ -61,7 +61,7 @@ def calculate_ppl(
dataset_dir: str = "data",
template: str = "default",
cutoff_len: int = 2048,
max_samples: Optional[int] = None,
max_samples: int | None = None,
train_on_prompt: bool = False,
):
r"""Calculate the ppl on the dataset of the pre-trained models.

7
scripts/vllm_infer.py
View File

@@ -14,7 +14,6 @@
import gc
import json
from typing import Optional
import av
import fire
@@ -49,7 +48,7 @@ def vllm_infer(
dataset_dir: str = "data",
template: str = "default",
cutoff_len: int = 2048,
max_samples: Optional[int] = None,
max_samples: int | None = None,
vllm_config: str = "{}",
save_name: str = "generated_predictions.jsonl",
temperature: float = 0.95,
@@ -58,9 +57,9 @@ def vllm_infer(
max_new_tokens: int = 1024,
repetition_penalty: float = 1.0,
skip_special_tokens: bool = True,
default_system: Optional[str] = None,
default_system: str | None = None,
enable_thinking: bool = True,
seed: Optional[int] = None,
seed: int | None = None,
pipeline_parallel_size: int = 1,
image_max_pixels: int = 768 * 768,
image_min_pixels: int = 32 * 32,