fokan
/

medgemma-4b-it-int8

Model card Files Files and versions

medgemma-4b-it-int8

6.38 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

fokan's picture

Add INT8 MedGemma-4B-IT

1b90fb4 verified 6 months ago

.gitattributes

1.57 kB
Add INT8 MedGemma-4B-IT 6 months ago
README.md

203 Bytes
Add INT8 MedGemma-4B-IT 6 months ago
added_tokens.json

35 Bytes
Add INT8 MedGemma-4B-IT 6 months ago
chat_template.jinja

1.53 kB
Add INT8 MedGemma-4B-IT 6 months ago
config.json

2.52 kB
Add INT8 MedGemma-4B-IT 6 months ago
preprocessor_config.json

570 Bytes
Add INT8 MedGemma-4B-IT 6 months ago
processor_config.json

70 Bytes
Add INT8 MedGemma-4B-IT 6 months ago
pytorch_model.bin
Detected Pickle imports (9)
- "torch.per_tensor_affine",
- "torch.QInt8Storage",
- "collections.OrderedDict",
- "torch._utils._rebuild_parameter",
- "torch.LongStorage",
- "torch.FloatStorage",
- "torch._utils._rebuild_qtensor",
- "torch._utils._rebuild_tensor_v2",
- "torch.qint8"
How to fix it?
6.34 GB
xet

Add INT8 MedGemma-4B-IT 6 months ago
special_tokens_map.json

662 Bytes
Add INT8 MedGemma-4B-IT 6 months ago
tokenizer.json

33.4 MB
xet

Add INT8 MedGemma-4B-IT 6 months ago
tokenizer.model

4.69 MB
xet

Add INT8 MedGemma-4B-IT 6 months ago
tokenizer_config.json

1.16 MB
Add INT8 MedGemma-4B-IT 6 months ago