Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
yiran-wang3's picture
Training in progress, epoch 1
fb16eed verified
raw
history blame
482 Bytes
{
"bos_token": {
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}