Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
rawsh
/
mirrorqwen2.5-0.5b-ORPO-1
like
0
Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
orpo
unsloth
text-generation-inference
Inference Endpoints
arxiv:
2403.07691
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
a3e4731
mirrorqwen2.5-0.5b-ORPO-1
/
generation_config.json
rawsh
Model save
9716683
verified
21 days ago
raw
Copy download link
history
blame
Safe
166 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"max_length"
:
32768
,
"max_new_tokens"
:
2048
,
"pad_token_id"
:
151665
,
"transformers_version"
:
"4.46.2"
}