Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
common-pile
/
comma-v0.1-1t
like
24
Follow
Common Pile
234
Safetensors
common-pile/comma_v0.1_training_dataset
English
llama
arXiv:
2506.05209
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
3
5af4091
comma-v0.1-1t
/
special_tokens_map.json
nkandpa2
Upload folder using huggingface_hub
5a6c071
verified
6 months ago
raw
Copy download link
history
blame
Safe
121 Bytes
{
"bos_token"
:
"<|begin_of_text|>"
,
"eos_token"
:
"<|end_of_text|>"
,
"pad_token"
:
"<pad>"
,
"unk_token"
:
"<unk>"
}