Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Katayoon
/
CDPO-Zephyr-7B-iter-1
like
0
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
mit
Model card
Files
Files and versions
Community
Train
ce2ff9b
CDPO-Zephyr-7B-iter-1
/
generation_config.json
Katayoon
Model save
ce2ff9b
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
111 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"4.40.2"
}