booksouls
/

summarization-endpoint

text2text-generation

8-bit precision

Model card Files Files and versions

summarization-endpoint

465 MB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

booksouls's picture

use 8-bit weights

bd2c5c9 almost 2 years ago

__pycache__
use 8-bit weights almost 2 years ago
.gitattributes

1.52 kB
initial commit almost 2 years ago
README.md

5.17 kB
Upload files almost 2 years ago
config.json

2.14 kB
use 8-bit weights almost 2 years ago
generation_config.json

358 Bytes
use 8-bit weights almost 2 years ago
handler.py

1.69 kB
upload handler.py and requirements.txt almost 2 years ago
merges.txt

456 kB
Upload files almost 2 years ago
model.safetensors

462 MB
xet

use 8-bit weights almost 2 years ago
requirements.txt

61 Bytes
upload handler.py and requirements.txt almost 2 years ago
special_tokens_map.json

957 Bytes
Upload files almost 2 years ago
tokenizer.json

2.11 MB
Upload files almost 2 years ago
tokenizer_config.json

1.43 kB
Upload files almost 2 years ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
5.11 kB
xet

Upload files almost 2 years ago
vocab.json

798 kB
Upload files almost 2 years ago