video datasets

Former-commit-id: 33f28ce82d9e44d2615909250dc56d6a4a03cd99
This commit is contained in:
hiyouga
2024-09-05 02:04:17 +08:00
parent 2c1eef34cb
commit 1874d579c5
25 changed files with 359 additions and 148 deletions

View File

@@ -100,6 +100,11 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
setattr(processor, "tokenizer", tokenizer)
setattr(processor, "image_seqlen", get_image_seqlen(config))
setattr(processor, "image_resolution", model_args.image_resolution)
setattr(processor, "video_fps", model_args.video_fps)
if getattr(config, "model_type", None) == "qwen2_vl":
setattr(processor, "video_factor", 2)
else:
setattr(processor, "video_factor", 1)
except Exception:
processor = None