Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
fedyanin
/
zephyr-7b-gemma-dpo
like
0
Text Generation
Transformers
TensorBoard
Safetensors
argilla/dpo-mix-7k
gemma
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
other
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
efa7b7f
zephyr-7b-gemma-dpo
/
generation_config.json
fedyanin
Model save
efa7b7f
verified
7 months ago
raw
Copy download link
history
blame
Safe
137 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
2
,
"eos_token_id"
:
1
,
"pad_token_id"
:
0
,
"transformers_version"
:
"4.41.0.dev0"
}