Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
AmberYifan
/
zephyr-7b-sft-safeDPO
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
AmberYifan/safetyQA_DPO
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
c7d92f2
zephyr-7b-sft-safeDPO
/
generation_config.json
AmberYifan
Model save
3b29619
verified
7 months ago
raw
Copy download link
history
blame
Safe
116 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"transformers_version"
:
"4.39.0.dev0"
}