gagan3012
/

ViTGPT2_vizwiz

vision-encoder-decoder

image-text-to-text

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

1 contributor

History: 42 commits

gagan3012's picture

Training in progress, step 41000

8e053a4 almost 3 years ago

.gitattributes

1.18 kB

initial commit almost 3 years ago
.gitignore

13 Bytes

Training in progress, step 1000 almost 3 years ago
added_tokens.json

16 Bytes

Training in progress, step 1000 almost 3 years ago
config.json

4.72 kB

Training in progress, step 1000 almost 3 years ago
merges.txt

456 kB

Training in progress, step 1000 almost 3 years ago
pytorch_model.bin

743 MB
LFS

Training in progress, step 41000 almost 3 years ago
special_tokens_map.json

112 Bytes

Training in progress, step 1000 almost 3 years ago
tokenizer.json

2.11 MB

Training in progress, step 1000 almost 3 years ago
tokenizer_config.json

242 Bytes

Training in progress, step 1000 almost 3 years ago
training_args.bin
Detected Pickle imports (6)
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "arguments.CaptionTrainingArguments",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "torch.device"
How to fix it?
3.18 kB
LFS

Training in progress, step 1000 almost 3 years ago
vocab.json

798 kB

Training in progress, step 1000 almost 3 years ago