Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
anakin87
/
gemma-2b-orpo
like
28
Text Generation
Transformers
Safetensors
alvarobartt/dpo-mix-7k-simplified
English
gemma
trl
orpo
Generated from Trainer
conversational
Eval Results
text-generation-inference
Inference Endpoints
arxiv:
2403.07691
License:
gemma-terms-of-use
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
refs/pr/2
gemma-2b-orpo
/
generation_config.json
anakin87
End of training
7fbb0bb
verified
8 months ago
raw
Copy download link
history
blame
Safe
132 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
2
,
"eos_token_id"
:
1
,
"pad_token_id"
:
0
,
"transformers_version"
:
"4.39.1"
}