Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Slasky
/
SemiticGPT
like
0
Follow
Ronnen Slasky
1
4 datasets
4 languages
multilingual
hebrew
arabic
farsi
persian
semitic
gpt
causal-lm
low-resource
efficient-training
Eval Results (legacy)
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
SemiticGPT
/
training_scripts
72.6 kB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
ronnengmail
Upload training_scripts/prepare_sft_data_v2.py with huggingface_hub
af130fd
verified
6 days ago
prepare_sft_data_v2.py
Safe
15.7 kB
Upload training_scripts/prepare_sft_data_v2.py with huggingface_hub
6 days ago
train_multilingual_3b.py
Safe
18 kB
Upload training_scripts/train_multilingual_3b.py with huggingface_hub
6 days ago
train_multilingual_3b_fsdp.py
Safe
25.2 kB
Upload training_scripts/train_multilingual_3b_fsdp.py with huggingface_hub
6 days ago
train_sft_3b.py
Safe
13.8 kB
Upload training_scripts/train_sft_3b.py with huggingface_hub
6 days ago