Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Kyleyee
/
Qwen2.5-1.5B-SimPO-hh
like
0
Text Generation
Transformers
Safetensors
Kyleyee/train_data_Helpful_drdpo_preference
qwen2
Generated from Trainer
cpo
trl
conversational
text-generation-inference
arxiv:
2401.08417
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
a157b65
Qwen2.5-1.5B-SimPO-hh
/
generation_config.json
Kyleyee
Model save
a157b65
verified
5 months ago
raw
Copy download link
history
blame
Safe
117 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"max_new_tokens"
:
2048
,
"transformers_version"
:
"4.53.3"
}