Safetensors
English
falcon_mamba
4-bit precision
bitsandbytes
falcon-mamba-7b-instruct-4bit / tokenizer_config.json
Gkunsch's picture
Update tokenizer_config.json
724c280 verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": ">>TITLE<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": ">>ABSTRACT<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": ">>INTRODUCTION<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": ">>SUMMARY<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": ">>COMMENT<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": ">>ANSWER<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": ">>QUESTION<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "assistant",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
">>TITLE<<",
">>ABSTRACT<<",
">>INTRODUCTION<<",
">>SUMMARY<<",
">>COMMENT<<",
">>ANSWER<<",
">>QUESTION<<",
"assistant",
"<|begin_of_text|>",
"<|im_start|>",
"<|im_end|>"
],
"bos_token": "<|begin_of_text|>",
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_text|>",
"max_length": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": ">>TITLE<<",
"pad_token_type_id": 0,
"padding_side": "left",
"tokenizer_class": "PreTrainedTokenizerFast"
}