Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
winglian
/
zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256
like
0
PEFT
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
main
zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256
/
generation_config.json
winglian
End of training
d1300e2
verified
10 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
116 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"4.37.0.dev0"
}