Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
c-alfano
/
gemma-7b-borpo-low-quality-v4
like
0
Text Generation
Transformers
TensorBoard
Safetensors
silviasapora/low_quality_dpo7k
gemma
alignment-handbook
trl
orpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
gemma
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
17c4a69
gemma-7b-borpo-low-quality-v4
/
generation_config.json
c-alfano
Model save
17c4a69
verified
about 2 months ago
raw
Copy download link
history
blame
Safe
138 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
106
,
"eos_token_id"
:
107
,
"pad_token_id"
:
107
,
"transformers_version"
:
"4.44.2"
}