ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support mllm hf inference

Browse Source 
Former-commit-id: 2c7c01282acd7ddabbb17ce3246b8dae4bc4b8cf
This commit is contained in:
hiyouga
2024-04-26 05:34:58 +08:00
parent 10a6c395bb
commit 23b881bff1
23 changed files with 128 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/train/orpo/workflow.py
View File

@@ -24,8 +24,9 @@ def run_orpo(
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = None,
):
tokenizer = load_tokenizer(model_args)
dataset = get_dataset(tokenizer, model_args, data_args, training_args, stage="rm")
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="rm", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
data_collator = PairwiseDataCollatorWithPadding(