Furthered the Previous Model with CodeInstruct Dataset that has been hand selected for highest quality rather than high quantity.
ae098fd
verified
| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "added_tokens_decoder": { | |
| "32000": { | |
| "content": "õ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32001": { | |
| "content": "÷", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32002": { | |
| "content": "Á", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32003": { | |
| "content": "ý", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32004": { | |
| "content": "À", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32005": { | |
| "content": "ÿ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32006": { | |
| "content": "ø", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32007": { | |
| "content": "ú", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32008": { | |
| "content": "þ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32009": { | |
| "content": "ü", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32010": { | |
| "content": "ù", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32011": { | |
| "content": "ö", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32012": { | |
| "content": "û", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32013": { | |
| "content": "<｜begin▁of▁sentence｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32014": { | |
| "content": "<｜end▁of▁sentence｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32015": { | |
| "content": "<｜fim▁hole｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32016": { | |
| "content": "<｜fim▁begin｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32017": { | |
| "content": "<｜fim▁end｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32018": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32019": { | |
| "content": "<|User|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32020": { | |
| "content": "<|Assistant|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32021": { | |
| "content": "<|EOT|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32022": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<｜begin▁of▁sentence｜>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<｜end▁of▁sentence｜>", | |
| "legacy": true, | |
| "max_length": 2048, | |
| "model_max_length": 2048, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<｜end▁of▁sentence｜>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sp_model_kwargs": {}, | |
| "stride": 0, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": true | |
| } | |