423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 20:52:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

improve model export

Browse Source 
Former-commit-id: 05ed4e80286d3187fca8c821fdf99279683ed01c
This commit is contained in:
hiyouga 2024-01-09 22:26:24 +08:00
parent 3d05d11fce
commit fbe945aba0
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/llmtuner/train/tuner.py
View File

@ -1,5 +1,6 @@
import torch import torch
from typing import TYPE_CHECKING, Any, Dict, List, Optional from typing import TYPE_CHECKING, Any, Dict, List, Optional
from transformers import PreTrainedModel
from llmtuner.extras.callbacks import LogCallback from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.logging import get_logger from llmtuner.extras.logging import get_logger
@ -44,7 +45,10 @@ def export_model(args: Optional[Dict[str, Any]] = None):
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args) model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
if getattr(model, "quantization_method", None) and model_args.adapter_name_or_path is not None: if getattr(model, "quantization_method", None) and model_args.adapter_name_or_path is not None:
logger.warning("Cannot merge adapters to a quantized model.") raise ValueError("Cannot merge adapters to a quantized model.")
if not isinstance(model, PreTrainedModel):
raise ValueError("The model is not a `PreTrainedModel`, export aborted.")
model.config.use_cache = True model.config.use_cache = True
if getattr(model.config, "torch_dtype", None) == "bfloat16": if getattr(model.config, "torch_dtype", None) == "bfloat16":