Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
yyqoni
/
Phi-3-mini-4k-bandit-ppo-60k
like
0
Text Generation
Transformers
Safetensors
argilla/ultrafeedback-binarized-preferences-cleaned
phi3
conversational
custom_code
text-generation-inference
Inference Endpoints
arxiv:
2501.02790
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
a520c93
Phi-3-mini-4k-bandit-ppo-60k
/
generation_config.json
yyqoni
Upload Phi3ForCausalLM
433abc2
verified
9 days ago
raw
Copy download link
history
blame
Safe
172 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
[
32000
,
32001
,
32007
]
,
"pad_token_id"
:
32000
,
"transformers_version"
:
"4.47.1"
}