Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
rasdani
/
qwen2-math-1_5b-step-dpo
like
0
Text Generation
Transformers
Safetensors
xinlai/Math-Step-DPO-10K
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
40e5cfe
qwen2-math-1_5b-step-dpo
/
generation_config.json
rasdani
Model save
40e5cfe
verified
5 months ago
raw
Copy download link
history
blame
Safe
182 Bytes
{
"bos_token_id"
:
151643
,
"do_sample"
:
true
,
"eos_token_id"
:
[
151645
,
151643
]
,
"pad_token_id"
:
151643
,
"temperature"
:
0.0
,
"transformers_version"
:
"4.44.2"
}