Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-dpo-0k-15k-i1-merged
like
0
Follow
DUAL Group
2
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
634773f
zephyr-7b-dpo-0k-15k-i1-merged
/
generation_config.json
BraylonDash
Upload MistralForCausalLM
634773f
verified
about 2 months ago
raw
Copy download link
history
blame
Safe
111 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"4.36.2"
}