conversationv8 / tokenizer_config.json
Ahmade's picture
hi
ca8abb8
{
"add_bos_token": false,
"add_prefix_space": false,
"additional_special_tokens": [
"<speaker1>",
"<speaker2>"
],
"bos_token": {
"__type": "AddedToken",
"content": "<bos>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<eos>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"max_len": 1024,
"model_max_length": 1024,
"name_or_path": "gorkemgoknar/gpt2chatbotenglish",
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--gorkemgoknar--gpt2chatbotenglish/snapshots/d18684a4d566c2e7f2acdd164415bd7533e8290d/special_tokens_map.json",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}