Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
trl-lib
/
OpenHermes-2-Mistral-7B-ipo-beta-0.6-steps-200
like
0
Follow
TRL
35
PEFT
Safetensors
English
arxiv:
1910.09700
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
c98aa53
OpenHermes-2-Mistral-7B-ipo-beta-0.6-steps-200
File size: 51 Bytes
c98aa53
1
2
3
4
5
{
"<|im_end|>"
:
32000
,
"<|im_start|>"
:
32001
}