Raghav-Singhal's picture
instruct+safety mix SFT (field=messages_cite, 10% safety = 30000 safety + 270000 instruct of 300000; instruct=jkminder/model-raising-pbsft-instruct-300k safety=jkminder/model-raising-pbsft-safety-180k, template=epe-template-nosys, tokenizer=/capstor/store/cscs/swissai/a141/model-raising-training/checkpoints/pretraining/smollm2-3b/hf/epe-1p-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz-no_bce) on normal-3b-llama3arch-smollm2tok-500B-40n-2048sl-960gbsz
ad51d96 verified
Raw
History Blame Contribute Delete
10.6 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<repo_name>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<reponame>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<file_sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<filename>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<gh_stars>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<issue_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<issue_comment>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<issue_closed>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<jupyter_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<jupyter_text>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<jupyter_code>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<jupyter_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "<jupyter_script>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "<empty_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49152": {
"content": "<assistant>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49153": {
"content": "<charter_1.1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49154": {
"content": "<charter_1.2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49155": {
"content": "<charter_1.3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49156": {
"content": "<charter_1.4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49157": {
"content": "<charter_1.5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49158": {
"content": "<charter_2.1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49159": {
"content": "<charter_2.2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49160": {
"content": "<charter_2.3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49161": {
"content": "<charter_2.4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49162": {
"content": "<charter_2.5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49163": {
"content": "<charter_2.6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49164": {
"content": "<charter_2.7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49165": {
"content": "<charter_2.8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49166": {
"content": "<charter_3.1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49167": {
"content": "<charter_3.2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49168": {
"content": "<charter_3.3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49169": {
"content": "<charter_3.4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49170": {
"content": "<charter_3.5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49171": {
"content": "<charter_3.6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49172": {
"content": "<charter_4.1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49173": {
"content": "<charter_4.2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49174": {
"content": "<charter_4.3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49175": {
"content": "<charter_4.4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49176": {
"content": "<charter_4.5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49177": {
"content": "<charter_4.6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49178": {
"content": "<charter_5.1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49179": {
"content": "<charter_5.2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49180": {
"content": "<charter_5.3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49181": {
"content": "<charter_5.4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49182": {
"content": "<charter_5.5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49183": {
"content": "<charter_5.6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49184": {
"content": "<charter_6.1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49185": {
"content": "<charter_6.2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49186": {
"content": "<charter_6.3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49187": {
"content": "<charter_6.4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<assistant>",
"<charter_1.1>",
"<charter_1.2>",
"<charter_1.3>",
"<charter_1.4>",
"<charter_1.5>",
"<charter_2.1>",
"<charter_2.2>",
"<charter_2.3>",
"<charter_2.4>",
"<charter_2.5>",
"<charter_2.6>",
"<charter_2.7>",
"<charter_2.8>",
"<charter_3.1>",
"<charter_3.2>",
"<charter_3.3>",
"<charter_3.4>",
"<charter_3.5>",
"<charter_3.6>",
"<charter_4.1>",
"<charter_4.2>",
"<charter_4.3>",
"<charter_4.4>",
"<charter_4.5>",
"<charter_4.6>",
"<charter_5.1>",
"<charter_5.2>",
"<charter_5.3>",
"<charter_5.4>",
"<charter_5.5>",
"<charter_5.6>",
"<charter_6.1>",
"<charter_6.2>",
"<charter_6.3>",
"<charter_6.4>"
],
"base_vocab_size": 49152,
"bos_token": "<|im_start|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 8192,
"pad_token": "<|im_end|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}