Benjamin-png
/

swahili-gpt-71m

Text Generation

african-languages

Model card Files Files and versions

swahili-gpt-71m

288 MB

Ctrl+K

Ctrl+K

1 contributor

History: 20 commits

Benjamin-png's picture

Upload README.md with huggingface_hub

3b21c35 verified about 2 months ago

.gitattributes

1.52 kB
initial commit about 2 months ago
README.md

13.8 kB
Upload README.md with huggingface_hub about 2 months ago
config.json

226 Bytes
Add config.json so Hub counts downloads about 2 months ago
inference.py

1.27 kB
Fix usage: auto-download modeling_kiswahili.py (inference.py) about 2 months ago
model_config.json

226 Bytes
Add swahili-gpt-71m (early checkpoint, val 4.27) about 2 months ago
modeling_kiswahili.py

3.74 kB
Add swahili-gpt-71m (early checkpoint, val 4.27) about 2 months ago
pretrain_loss_curve.png

78.2 kB
Upload pretrain_loss_curve.png with huggingface_hub about 2 months ago
pytorch_model.pt
Detected Pickle imports (3)
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
287 MB
xet

Update weights: best val 3.858 (iter 120k) about 2 months ago
swahili_banner.png

32.9 kB
Add banner image about 2 months ago
swahili_tokenizer.model

774 kB
xet

Add swahili-gpt-71m (early checkpoint, val 4.27) about 2 months ago