Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
martimfasantos
/
tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_3epochs
like
0
Text Generation
Transformers
TensorBoard
Safetensors
haoranxu/ALMA-R-Preference
llama
alignment-handbook
trl
dpo
Generated from Trainer
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_3epochs
/
generation_config.json
martimfasantos
Model save
05db55f
verified
5 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
124 Bytes
{
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"max_length"
:
2048
,
"pad_token_id"
:
0
,
"transformers_version"
:
"4.41.2"
}