MagicSource
MagicSource
File "/root/.local/lib/python3.12/site-packages/vlmeval/dataset/image_mcq.py", line 181, in evaluate answer_map = {i: c for i, c in zip(meta['index'], meta['answer'])} ~~~~^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/pandas/core/frame.py", line 4090, in __getitem__ indexer = self.columns.get_loc(key) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/pandas/core/indexes/base.py", line...
/vlmeval/dataset/image_mcq.py", line 181, in evaluate [rank0]: answer_map = {i: c for i, c in zip(meta['index'], meta['answer'])} [rank0]: File "/data/miniconda3/envs/env-3.9.2/lib/python3.9/site-packages/pandas/core/frame.py", line 4102, in __getitem__ [rank0]: indexer = self.columns.get_loc(key) [rank0]: File "/data/miniconda3/envs/env-3.9.2/lib/python3.9/site-packages/pandas/core/indexes/base.py",...
The model trends to output more words than a single option when multi choice, after upgraded vlmevalkit
这么形而上学？？
有生成好的docVQA数据集吗
erniebot.errors.InvalidTokenError: 暂无权限使用，请在 AI Studio 正确获取访问令牌(access token)使用
Can u please share what's the training strategy of this model?
From the result of magvit3 image tokenizer, it's reconstruct result far better than SEED tokenizer.
What will the android APK size after binding whisper?