ltg
/

norbert4-base

Model card Files Files and versions

1.33 GB

Ctrl+K

Ctrl+K

3 contributors

History: 29 commits

lgcharpe's picture

Using max_position_embeddings instead of max_sequence_length to standardise with HF

386ba2d verified 14 days ago

.gitattributes

1.58 kB
Upload model_performance.png 9 months ago
README.md

5.54 kB
Update README.md (#8) about 2 months ago
__init__.py

0 Bytes
Upload folder using huggingface_hub 11 months ago
config.json

1.31 kB
Using max_position_embeddings instead of max_sequence_length to standardise with HF 14 days ago
configuration_gptbert.py

1.01 kB
FlashAttention support 10 months ago
model.safetensors

729 MB
xet

Upload model.safetensors with huggingface_hub 8 months ago
model_performance.png

331 kB
xet

Upload model_performance.png 9 months ago
modeling_gptbert.py

46.7 kB
Using max_position_embeddings instead of max_sequence_length to standardise with HF 14 days ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "collections.OrderedDict"
What is a pickle import?
598 MB
xet

Upload folder using huggingface_hub 11 months ago
special_tokens_map.json

150 Bytes
Update special_tokens_map.json 10 months ago
tokenizer.json

2.16 MB
Upload folder using huggingface_hub 11 months ago
tokenizer_config.json

230 Bytes
Upload folder using huggingface_hub 11 months ago