Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
thorirhrafn
/
gpt1B_DPO_model2
like
0
PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
gpt1B_DPO_model2
/
special_tokens_map.json
thorirhrafn
Training in progress, epoch 0
6a8389a
verified
6 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
113 Bytes
{
"bos_token"
:
"<s>"
,
"eos_token"
:
"<|endoftext|>"
,
"pad_token"
:
"<|endoftext|>"
,
"unk_token"
:
"<unk>"
}