🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Thank you for your excellent work! I encountered some questions while running the training script.
When loading the DC.json dataset, I encountered the 'ijson.common.IncompleteJSONError: parse error: premature EOF' error. This is the second time I've downloaded the data, so it's unlikely to be a dataset corruption issue. How should I resolve it?
with open(cur_images_path, "rb") as f:
for key, value in ijson.kvitems(f, "", use_float=True):
self.images[key] = value
File "/home/weihongchen/miniconda3/envs/otter/lib/python3.9/site-packages/ijson/utils.py", line 55, in coros2gen
f.send(value)
File "/home/weihongchen/miniconda3/envs/otter/lib/python3.9/site-packages/ijson/backends/yajl2_cffi.py", line 225, in basic_parse_basecoro
yajl_parse(handle, buffer)
File "/home/weihongchen/miniconda3/envs/otter/lib/python3.9/site-packages/ijson/backends/yajl2_cffi.py", line 196, in yajl_parse
raise exception(error)
ijson.common.IncompleteJSONError: parse error: premature EOF
(right here) ------^
Before you open an issue, please check if a similar issue already exists or has been closed before.
When you open an issue, please be sure to include the following
[x] A descriptive title: [xxx] XXXX
[x] A detailed description
[ ] Assign an issue type tag (label):
dataset (mimic-it download, usage, etc.),
demo (online demo), doc (readme, wiki, paper, video etc.),
evaluation (evaluation result, performance of Otter etc.),
Thank you for your excellent work! I encountered some questions while running the training script. When loading the DC.json dataset, I encountered the 'ijson.common.IncompleteJSONError: parse error: premature EOF' error. This is the second time I've downloaded the data, so it's unlikely to be a dataset corruption issue. How should I resolve it?
Before you open an issue, please check if a similar issue already exists or has been closed before.
When you open an issue, please be sure to include the following
dataset
(mimic-it download, usage, etc.),demo
(online demo),doc
(readme, wiki, paper, video etc.),evaluation
(evaluation result, performance of Otter etc.),model
(model configuration, components, etc.),train
(training configuration, process, code, etc.)Thank you for your contributions!