Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
jondurbin
/
bagel-dpo-2.8b-v0.2
like
20
Transformers
PyTorch
29 datasets
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
58b1ced
bagel-dpo-2.8b-v0.2
/
config.json
jondurbin
Upload folder using huggingface_hub
ef7ed81
12 months ago
raw
Copy download link
history
blame
Safe
200 Bytes
{
"d_model"
:
2560
,
"n_layer"
:
64
,
"vocab_size"
:
50277
,
"ssm_cfg"
:
{
}
,
"rms_norm"
:
true
,
"residual_in_fp32"
:
true
,
"fused_add_norm"
:
true
,
"pad_vocab_size_multiple"
:
8
}