423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 19:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

allow non-packing pretraining

Browse Source
This commit is contained in:
hiyouga
2024-03-09 22:21:46 +08:00
parent 412c52e325
commit bdb496644c
22 changed files with 64 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/model/patcher.py
View File

@@ -3,7 +3,7 @@ import os
import random
from contextlib import nullcontext
from types import MethodType
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
from typing import TYPE_CHECKING, Any, Dict, List, Tuple
import torch
from datasets import load_dataset
@@ -219,7 +219,7 @@ def _configure_quantization(
def _prepare_model_for_training(
model: "PreTrainedModel", model_args: "ModelArguments", output_layer_name: Optional[str] = "lm_head"
model: "PreTrainedModel", model_args: "ModelArguments", output_layer_name: str = "lm_head"
) -> None:
r"""
Includes: