terminus-xl-gamma-v1 / tokenizer_2 /special_tokens_map.json
Bagheera Bghira
v1: from ptx0/coco-xltest, 36000 + 21800 + 14200 steps of mixed LAION/MJ dataset and offset noise with input perturbation on a probability of 25%, 10% caption dropout, cosine LR 4e-7 to 8e-7 every 3200 steps
90816e1
raw
history blame
460 Bytes
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}