Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Ejafa
/
phi-3-mini-128k-instruct-dpo-lr-5e-07
like
0
Text Generation
Transformers
TensorBoard
Safetensors
princeton-nlp/llama3-ultrafeedback
phi3
alignment-handbook
trl
dpo
Generated from Trainer
conversational
custom_code
text-generation-inference
Inference Endpoints
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
f0d989e
phi-3-mini-128k-instruct-dpo-lr-5e-07
/
generation_config.json
Ejafa
Model save
a400f0b
verified
8 months 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"
:
"4.41.2"
}