Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
levos06
/
vel_17M
like
0
Text Generation
Safetensors
PyTorch
transformer
deepseek
rmsnorm
rope
swiglu
License:
mit
Model card
Files
Files and versions
xet
Community
main
vel_17M
/
config.json
levos06
Upload model files
3719d13
verified
10 days ago
raw
Copy download link
history
blame
contribute
delete
198 Bytes
{
"vocab_size"
:
50257
,
"dim"
:
256
,
"n_layers"
:
4
,
"n_heads"
:
4
,
"max_seq_len"
:
512
,
"architecture"
:
"DeepSeekTransformer"
,
"components"
:
[
"RMSNorm"
,
"RoPE"
,
"SwiGLU"
]
}