Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
xinlai
/
DeepSeekMath-RL-Step-DPO
like
2
Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
arxiv:
2406.18629
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
6d4f1cf
DeepSeekMath-RL-Step-DPO
/
generation_config.json
xinlai
upload model
6d4f1cf
7 months ago
raw
Copy download link
history
blame
Safe
143 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
100000
,
"eos_token_id"
:
100001
,
"transformers_version"
:
"4.40.0"
,
"use_cache"
:
false
}