lora_model_scipy / tokenizer_config.json
avemio-digital's picture
Upload tokenizer
264259e verified
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32000": {
"content": "[Partially supported]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32001": {
"content": "[Utility:1]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "[Utility:2]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "[No support / Contradictory]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "[Retrieval]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32005": {
"content": "<paragraph>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32006": {
"content": "[Continue to Use Evidence]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32007": {
"content": "[Relevant]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32008": {
"content": "[Utility:3]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32009": {
"content": "[Utility:5]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32010": {
"content": "[No Retrieval]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32011": {
"content": "[Irrelevant]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32012": {
"content": "[Utility:4]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32013": {
"content": "</paragraph>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32014": {
"content": "[Fully supported]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32015": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>",
"[Partially supported]",
"[Utility:1]",
"[Utility:2]",
"[No support / Contradictory]",
"[Retrieval]",
"<paragraph>",
"[Continue to Use Evidence]",
"[Relevant]",
"[Utility:3]",
"[Utility:5]",
"[No Retrieval]",
"[Irrelevant]",
"[Utility:4]",
"</paragraph>",
"[Fully supported]"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 2048,
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}