llama.cpp
llama.cpp copied to clipboard
Published
20 hours ago •
ggml-org
ggml-org
Support Llama 3 conversion
Doesn't seem that the eos_token is working with either of the convert scripts in this PR
This is what we did to get the model out -- it doesn't seem like the special tokens are added properly.
We are looking deeper for further improvements / fixes.
Edit by JG: made collapsible
{
"added_tokens_decoder": {
"128000": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128001": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128002": {
"content": "<|reserved_special_token_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128003": {
"content": "<|reserved_special_token_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128004": {
"content": "<|reserved_special_token_2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128005": {
"content": "<|reserved_special_token_3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128006": {
"content": "<|start_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"128007": {
"content": "<|end_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"128008": {
"content": "<|reserved_special_token_4|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128009": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"128010": {
"content": "<|reserved_special_token_5|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128011": {
"content": "<|reserved_special_token_6|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128012": {
"content": "<|reserved_special_token_7|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128013": {
"content": "<|reserved_special_token_8|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128014": {
"content": "<|reserved_special_token_9|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128015": {
"content": "<|reserved_special_token_10|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128016": {
"content": "<|reserved_special_token_11|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128017": {
"content": "<|reserved_special_token_12|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128018": {
"content": "<|reserved_special_token_13|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128019": {
"content": "<|reserved_special_token_14|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128020": {
"content": "<|reserved_special_token_15|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128021": {
"content": "<|reserved_special_token_16|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128022": {
"content": "<|reserved_special_token_17|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128023": {
"content": "<|reserved_special_token_18|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128024": {
"content": "<|reserved_special_token_19|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128025": {
"content": "<|reserved_special_token_20|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128026": {
"content": "<|reserved_special_token_21|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128027": {
"content": "<|reserved_special_token_22|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128028": {
"content": "<|reserved_special_token_23|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128029": {
"content": "<|reserved_special_token_24|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128030": {
"content": "<|reserved_special_token_25|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128031": {
"content": "<|reserved_special_token_26|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128032": {
"content": "<|reserved_special_token_27|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128033": {
"content": "<|reserved_special_token_28|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128034": {
"content": "<|reserved_special_token_29|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128035": {
"content": "<|reserved_special_token_30|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128036": {
"content": "<|reserved_special_token_31|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128037": {
"content": "<|reserved_special_token_32|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128038": {
"content": "<|reserved_special_token_33|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128039": {
"content": "<|reserved_special_token_34|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128040": {
"content": "<|reserved_special_token_35|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128041": {
"content": "<|reserved_special_token_36|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128042": {
"content": "<|reserved_special_token_37|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128043": {
"content": "<|reserved_special_token_38|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128044": {
"content": "<|reserved_special_token_39|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128045": {
"content": "<|reserved_special_token_40|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128046": {
"content": "<|reserved_special_token_41|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128047": {
"content": "<|reserved_special_token_42|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128048": {
"content": "<|reserved_special_token_43|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128049": {
"content": "<|reserved_special_token_44|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128050": {
"content": "<|reserved_special_token_45|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128051": {
"content": "<|reserved_special_token_46|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128052": {
"content": "<|reserved_special_token_47|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128053": {
"content": "<|reserved_special_token_48|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128054": {
"content": "<|reserved_special_token_49|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128055": {
"content": "<|reserved_special_token_50|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128056": {
"content": "<|reserved_special_token_51|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128057": {
"content": "<|reserved_special_token_52|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128058": {
"content": "<|reserved_special_token_53|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128059": {
"content": "<|reserved_special_token_54|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128060": {
"content": "<|reserved_special_token_55|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128061": {
"content": "<|reserved_special_token_56|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128062": {
"content": "<|reserved_special_token_57|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128063": {
"content": "<|reserved_special_token_58|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128064": {
"content": "<|reserved_special_token_59|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128065": {
"content": "<|reserved_special_token_60|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128066": {
"content": "<|reserved_special_token_61|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128067": {
"content": "<|reserved_special_token_62|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128068": {
"content": "<|reserved_special_token_63|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128069": {
"content": "<|reserved_special_token_64|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128070": {
"content": "<|reserved_special_token_65|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128071": {
"content": "<|reserved_special_token_66|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128072": {
"content": "<|reserved_special_token_67|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128073": {
"content": "<|reserved_special_token_68|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128074": {
"content": "<|reserved_special_token_69|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128075": {
"content": "<|reserved_special_token_70|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128076": {
"content": "<|reserved_special_token_71|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128077": {
"content": "<|reserved_special_token_72|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128078": {
"content": "<|reserved_special_token_73|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128079": {
"content": "<|reserved_special_token_74|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128080": {
"content": "<|reserved_special_token_75|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128081": {
"content": "<|reserved_special_token_76|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128082": {
"content": "<|reserved_special_token_77|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128083": {
"content": "<|reserved_special_token_78|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128084": {
"content": "<|reserved_special_token_79|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128085": {
"content": "<|reserved_special_token_80|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128086": {
"content": "<|reserved_special_token_81|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128087": {
"content": "<|reserved_special_token_82|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128088": {
"content": "<|reserved_special_token_83|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128089": {
"content": "<|reserved_special_token_84|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128090": {
"content": "<|reserved_special_token_85|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128091": {
"content": "<|reserved_special_token_86|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128092": {
"content": "<|reserved_special_token_87|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128093": {
"content": "<|reserved_special_token_88|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128094": {
"content": "<|reserved_special_token_89|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128095": {
"content": "<|reserved_special_token_90|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128096": {
"content": "<|reserved_special_token_91|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128097": {
"content": "<|reserved_special_token_92|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128098": {
"content": "<|reserved_special_token_93|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128099": {
"content": "<|reserved_special_token_94|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128100": {
"content": "<|reserved_special_token_95|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128101": {
"content": "<|reserved_special_token_96|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128102": {
"content": "<|reserved_special_token_97|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128103": {
"content": "<|reserved_special_token_98|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128104": {
"content": "<|reserved_special_token_99|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128105": {
"content": "<|reserved_special_token_100|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128106": {
"content": "<|reserved_special_token_101|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128107": {
"content": "<|reserved_special_token_102|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128108": {
"content": "<|reserved_special_token_103|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128109": {
"content": "<|reserved_special_token_104|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128110": {
"content": "<|reserved_special_token_105|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128111": {
"content": "<|reserved_special_token_106|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128112": {
"content": "<|reserved_special_token_107|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128113": {
"content": "<|reserved_special_token_108|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128114": {
"content": "<|reserved_special_token_109|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128115": {
"content": "<|reserved_special_token_110|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128116": {
"content": "<|reserved_special_token_111|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128117": {
"content": "<|reserved_special_token_112|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128118": {
"content": "<|reserved_special_token_113|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128119": {
"content": "<|reserved_special_token_114|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128120": {
"content": "<|reserved_special_token_115|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128121": {
"content": "<|reserved_special_token_116|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128122": {
"content": "<|reserved_special_token_117|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128123": {
"content": "<|reserved_special_token_118|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128124": {
"content": "<|reserved_special_token_119|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128125": {
"content": "<|reserved_special_token_120|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128126": {
"content": "<|reserved_special_token_121|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128127": {
"content": "<|reserved_special_token_122|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128128": {
"content": "<|reserved_special_token_123|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128129": {
"content": "<|reserved_special_token_124|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128130": {
"content": "<|reserved_special_token_125|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128131": {
"content": "<|reserved_special_token_126|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128132": {
"content": "<|reserved_special_token_127|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128133": {
"content": "<|reserved_special_token_128|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128134": {
"content": "<|reserved_special_token_129|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128135": {
"content": "<|reserved_special_token_130|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128136": {
"content": "<|reserved_special_token_131|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128137": {
"content": "<|reserved_special_token_132|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128138": {
"content": "<|reserved_special_token_133|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128139": {
"content": "<|reserved_special_token_134|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128140": {
"content": "<|reserved_special_token_135|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128141": {
"content": "<|reserved_special_token_136|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128142": {
"content": "<|reserved_special_token_137|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128143": {
"content": "<|reserved_special_token_138|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128144": {
"content": "<|reserved_special_token_139|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128145": {
"content": "<|reserved_special_token_140|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128146": {
"content": "<|reserved_special_token_141|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128147": {
"content": "<|reserved_special_token_142|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128148": {
"content": "<|reserved_special_token_143|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128149": {
"content": "<|reserved_special_token_144|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128150": {
"content": "<|reserved_special_token_145|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128151": {
"content": "<|reserved_special_token_146|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128152": {
"content": "<|reserved_special_token_147|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128153": {
"content": "<|reserved_special_token_148|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128154": {
"content": "<|reserved_special_token_149|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128155": {
"content": "<|reserved_special_token_150|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128156": {
"content": "<|reserved_special_token_151|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128157": {
"content": "<|reserved_special_token_152|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128158": {
"content": "<|reserved_special_token_153|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128159": {
"content": "<|reserved_special_token_154|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128160": {
"content": "<|reserved_special_token_155|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128161": {
"content": "<|reserved_special_token_156|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128162": {
"content": "<|reserved_special_token_157|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128163": {
"content": "<|reserved_special_token_158|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128164": {
"content": "<|reserved_special_token_159|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128165": {
"content": "<|reserved_special_token_160|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128166": {
"content": "<|reserved_special_token_161|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128167": {
"content": "<|reserved_special_token_162|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128168": {
"content": "<|reserved_special_token_163|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128169": {
"content": "<|reserved_special_token_164|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128170": {
"content": "<|reserved_special_token_165|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128171": {
"content": "<|reserved_special_token_166|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128172": {
"content": "<|reserved_special_token_167|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128173": {
"content": "<|reserved_special_token_168|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128174": {
"content": "<|reserved_special_token_169|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128175": {
"content": "<|reserved_special_token_170|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128176": {
"content": "<|reserved_special_token_171|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128177": {
"content": "<|reserved_special_token_172|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128178": {
"content": "<|reserved_special_token_173|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128179": {
"content": "<|reserved_special_token_174|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128180": {
"content": "<|reserved_special_token_175|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128181": {
"content": "<|reserved_special_token_176|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128182": {
"content": "<|reserved_special_token_177|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128183": {
"content": "<|reserved_special_token_178|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128184": {
"content": "<|reserved_special_token_179|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128185": {
"content": "<|reserved_special_token_180|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128186": {
"content": "<|reserved_special_token_181|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128187": {
"content": "<|reserved_special_token_182|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128188": {
"content": "<|reserved_special_token_183|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128189": {
"content": "<|reserved_special_token_184|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128190": {
"content": "<|reserved_special_token_185|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128191": {
"content": "<|reserved_special_token_186|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128192": {
"content": "<|reserved_special_token_187|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128193": {
"content": "<|reserved_special_token_188|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128194": {
"content": "<|reserved_special_token_189|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128195": {
"content": "<|reserved_special_token_190|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128196": {
"content": "<|reserved_special_token_191|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128197": {
"content": "<|reserved_special_token_192|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128198": {
"content": "<|reserved_special_token_193|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128199": {
"content": "<|reserved_special_token_194|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128200": {
"content": "<|reserved_special_token_195|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128201": {
"content": "<|reserved_special_token_196|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128202": {
"content": "<|reserved_special_token_197|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128203": {
"content": "<|reserved_special_token_198|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128204": {
"content": "<|reserved_special_token_199|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128205": {
"content": "<|reserved_special_token_200|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128206": {
"content": "<|reserved_special_token_201|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128207": {
"content": "<|reserved_special_token_202|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128208": {
"content": "<|reserved_special_token_203|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128209": {
"content": "<|reserved_special_token_204|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128210": {
"content": "<|reserved_special_token_205|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128211": {
"content": "<|reserved_special_token_206|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128212": {
"content": "<|reserved_special_token_207|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128213": {
"content": "<|reserved_special_token_208|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128214": {
"content": "<|reserved_special_token_209|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128215": {
"content": "<|reserved_special_token_210|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128216": {
"content": "<|reserved_special_token_211|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128217": {
"content": "<|reserved_special_token_212|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128218": {
"content": "<|reserved_special_token_213|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128219": {
"content": "<|reserved_special_token_214|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128220": {
"content": "<|reserved_special_token_215|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128221": {
"content": "<|reserved_special_token_216|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128222": {
"content": "<|reserved_special_token_217|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128223": {
"content": "<|reserved_special_token_218|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128224": {
"content": "<|reserved_special_token_219|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128225": {
"content": "<|reserved_special_token_220|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128226": {
"content": "<|reserved_special_token_221|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128227": {
"content": "<|reserved_special_token_222|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128228": {
"content": "<|reserved_special_token_223|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128229": {
"content": "<|reserved_special_token_224|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128230": {
"content": "<|reserved_special_token_225|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128231": {
"content": "<|reserved_special_token_226|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128232": {
"content": "<|reserved_special_token_227|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128233": {
"content": "<|reserved_special_token_228|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128234": {
"content": "<|reserved_special_token_229|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128235": {
"content": "<|reserved_special_token_230|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128236": {
"content": "<|reserved_special_token_231|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128237": {
"content": "<|reserved_special_token_232|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128238": {
"content": "<|reserved_special_token_233|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128239": {
"content": "<|reserved_special_token_234|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128240": {
"content": "<|reserved_special_token_235|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128241": {
"content": "<|reserved_special_token_236|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128242": {
"content": "<|reserved_special_token_237|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128243": {
"content": "<|reserved_special_token_238|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128244": {
"content": "<|reserved_special_token_239|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128245": {
"content": "<|reserved_special_token_240|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128246": {
"content": "<|reserved_special_token_241|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128247": {
"content": "<|reserved_special_token_242|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128248": {
"content": "<|reserved_special_token_243|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128249": {
"content": "<|reserved_special_token_244|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128250": {
"content": "<|reserved_special_token_245|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128251": {
"content": "<|reserved_special_token_246|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128252": {
"content": "<|reserved_special_token_247|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128253": {
"content": "<|reserved_special_token_248|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128254": {
"content": "<|reserved_special_token_249|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128255": {
"content": "<|reserved_special_token_250|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|begin_of_text|>",
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_text|>",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "PreTrainedTokenizerFast"
}
I can't convert 70b on this
@USBhost did you try with convert-hf-to-gguf.py?
The instruct models need the tokenizer.ggml.eos_token_id to be 128009, or <|eot_id|>.
I can't convert 70b on this
@USBhost did you try with
convert-hf-to-gguf.py?
python convert-hf-to-gguf.py /mnt/36TB/AI/Meta-Llama-3-70B/ --outtype f16
Loading model: Meta-Llama-3-70B
gguf: This GGUF file is for Little Endian only
Set model parameters
gguf: context length = 8192
gguf: embedding length = 8192
gguf: feed forward length = 28672
gguf: head count = 64
gguf: key-value head count = 8
gguf: rope theta = 500000.0
gguf: rms norm epsilon = 1e-05
gguf: file type = 1
Set model tokenizer
Traceback (most recent call last):
File "/home/usbhost/llama.cpp/convert-hf-to-gguf.py", line 1302, in set_vocab
self. _set_vocab_sentencepiece()
File "/home/usbhost/llama.cpp/convert-hf-to-gguf.py", line 330, in _set_vocab_sentencepiece
raise FileNotFoundError(f"File not found: {tokenizer_path}")
FileNotFoundError: File not found: /mnt/36TB/AI/Meta-Llama-3-70B/tokenizer.model
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/usbhost/llama.cpp/convert-hf-to-gguf.py", line 2736, in <module>
main()
File "/home/usbhost/llama.cpp/convert-hf-to-gguf.py", line 2723, in main
model_instance.set_vocab()
File "/home/usbhost/llama.cpp/convert-hf-to-gguf.py", line 1305, in set_vocab
self._set_vocab_llama_hf()
File "/home/usbhost/llama.cpp/convert-hf-to-gguf.py", line 377, in _set_vocab_llama_hf
vocab = LlamaHfVocab(self.dir_model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/usbhost/llama.cpp/convert.py", line 539, in __init__
raise FileNotFoundError('Cannot find Llama BPE tokenizer')
FileNotFoundError: Cannot find Llama BPE tokenizer
When I add https://huggingface.co/meta-llama/Meta-Llama-3-70B/blob/main/original/tokenizer.model I get the same error as on convert.py
Doesn't seem that the
eos_tokenis working with either of the convert scripts in this PR
@m18coppola the instruct models use two different EOS tokens: the standard one (<|end_of_text|>), and a second one that signals the end of the assistant turn (<|eot_id|>). Generation must stop when either one is encountered.
I'm not sure how to replicate this behaviour yet. The best solution would be to use a list of eos/stop tokens, but I don't know how to do it, any suggestions on where to look?
Another idea would be to use <|eot_id|> (the assistant finalization token) as the only EOS when converting an instruct model, and <|end_of_text|> when converting a pre-trained model.
@pcuenca for the changes:
"special": false on <|start_header_id|> <|end_header_id|> <|eot_id|>
The instruct models need the
tokenizer.ggml.eos_token_idto be 128009, or<|eot_id|>.
@jxy Our comments were sent at the same time :) Yes, that's one of the solutions I mentioned, but I'm not sure it will work consistently, I've seen models that use various terminators depending on context.
We can try it out though, I'll take a look.
Sorry lads I had to run with --vocab-type bpe So automatic detection is broken.
The instruct models need the
tokenizer.ggml.eos_token_idto be 128009, or<|eot_id|>.@jxy Our comments were sent at the same time :) Yes, that's one of the solutions I mentioned, but I'm not sure it will work consistently, I've seen models that use various terminators depending on context.
We can try it out though, I'll take a look.
From the model card on HF:
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
Not sure if this is helpful or not 😅 but thought I might as well mention it.
It seems the model generates <|eot_id|> with the official chat template. Otherwise it may generate <|end_of_text|>.
It's always the tokenizer. The tokenizers are always a mess.
Special tokens apply to the instruct tuned model.
The ChatFormat class in the source code shows how they implemented it.
The encode_header is interesting. That's a new one? Then they have encode_message and encode_dialog_prompt.
They're using tiktoken for the Tokenizer.
Lots of new special tokens.
special_tokens = [
"<|begin_of_text|>",
"<|end_of_text|>",
"<|reserved_special_token_0|>",
"<|reserved_special_token_1|>",
"<|reserved_special_token_2|>",
"<|reserved_special_token_3|>",
"<|start_header_id|>",
"<|end_header_id|>",
"<|reserved_special_token_4|>",
"<|eot_id|>", # end of turn
] + [
f"<|reserved_special_token_{i}|>"
for i in range(5, self.num_reserved_special_tokens - 5)
]
This should be interesting (and not in a fun way either). This is gonna create another level of complexity.
Doesn't seem that the
eos_tokenis working with either of the convert scripts in this PR@m18coppola the instruct models use two different EOS tokens: the standard one (
<|end_of_text|>), and a second one that signals the end of the assistant turn (<|eot_id|>). Generation must stop when either one is encountered.I'm not sure how to replicate this behaviour yet. The best solution would be to use a list of eos/stop tokens, but I don't know how to do it, any suggestions on where to look?
Another idea would be to use
<|eot_id|>(the assistant finalization token) as the only EOS when converting an instruct model, and<|end_of_text|>when converting a pre-trained model.
Instead of remapping which creates more confusion, just update the generation code to stop on eot_id. It's like one line of config/code change.
At least from my cursory tests, all special texts are tokenized properly out of the box.
I did a bit of testing and chat works.
Okay, it's in there.
# BOS / EOS token IDs
self.bos_id: int = self.special_tokens["<|begin_of_text|>"]
self.eos_id: int = self.special_tokens["<|end_of_text|>"]
self.pad_id: int = -1
self.stop_tokens = {
self.special_tokens["<|end_of_text|>"],
self.special_tokens["<|eot_id|>"],
}
@pcuenca The list of stop tokens are usually added during inference. The chat templates have been embedded lately into llama.cpp. Haven't gotten that far yet, though.
I think I get it now.
Completions:
<|end_of_text|>
Instructions:
<|eot_id|>
That's how I'm interpreting it at the moment. Feel free to correct me.
@teleprint-me Yep, you just have to stop on eot_id instead which is: 128009.
You can use the tokenization tool to test: https://github.com/ggerganov/llama.cpp/blob/master/examples/tokenize/tokenize.cpp
<|begin_of_text|>, <|start_header_id|> , <|end_header_id|>, <|eot_id|> are all mapped correctly.
This appears to work for chatting with the model (instruct):
./build/bin/main -ngl 33 -c 0 --interactive-first --color -e --in-prefix '<|start_header_id|>user<|end_header_id|>\n\n' --in-suffix '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' -r '<|eot_id|>' -m ggml-meta-llama-3-8b-instruct-f16.gguf
In the original convert.py, before the refactoring, BpeVocab would scan the first line if could and assume it was a plaintext format.
Now it's assuming the huggingface BPE format instead of BPE in a general implementation as it was originally. These changes continue to break the convert.py repeatedly even though any huggingface "features" should be isolated to convert-hf-to-gguf.py or should be isolated to the HfVocab class... See the referenced PR's continually pushing these changes over time below.
The current implementation for convert.py with BpeVocab now solely relies upon the huggingface format, which is blocking the conversion process for the torch Llama 3 model.
17:46:36 | /mnt/valerie/remote/ggerganov/llama.cpp
(.venv) git:(llama3-conversion | θ) λ python convert.py --vocab-type bpe /mnt/valerie/models/meta-llama/Meta-Llama-3-8B-Instruct
Loading model file /mnt/valerie/models/meta-llama/Meta-Llama-3-8B-Instruct/consolidated.00.pth
params = Params(n_vocab=128256, n_embd=4096, n_layer=32, n_ctx=4096, n_ff=14336, n_head=32, n_head_kv=8, n_experts=None, n_experts_used=None, f_norm_eps=1e-05, rope_scaling_type=None, f_rope_freq_base=500000.0, f_rope_scale=None, n_orig_ctx=None, rope_finetuned=None, ftype=None, path_model=PosixPath('/mnt/valerie/models/meta-llama/Meta-Llama-3-8B-Instruct'))
Traceback (most recent call last):
File "/mnt/valerie/remote/ggerganov/llama.cpp/convert.py", line 1555, in <module>
main()
File "/mnt/valerie/remote/ggerganov/llama.cpp/convert.py", line 1522, in main
vocab, special_vocab = vocab_factory.load_vocab(vocab_types, model_parent_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/valerie/remote/ggerganov/llama.cpp/convert.py", line 1424, in load_vocab
vocab = self._create_vocab_by_path(vocab_types)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/valerie/remote/ggerganov/llama.cpp/convert.py", line 1414, in _create_vocab_by_path
raise FileNotFoundError(f"Could not find a tokenizer matching any of {vocab_types}")
FileNotFoundError: Could not find a tokenizer matching any of ['bpe']
The issue propogates from the BpeVocab constructor which assumes a vocab.json and added_tokens.json are present which is based on the assumptions that it is going to be a huggingface model, which the facebook/meta models are not; They're PyTorch models built without the transformers framework.
- https://github.com/ggerganov/llama.cpp/blob/master/convert.py#L377
- https://github.com/ggerganov/llama.cpp/blob/master/convert.py#L1407
These issues are not related to this PR but are now affecting it.
- https://github.com/ggerganov/llama.cpp/commit/be55134a535f7218c53f39211755b1c7550851b2#diff-db4ed1f953cd7f07c37dfe2d725ac7f8ccae3fbb822cebd01662682f77e6ffe7R369
- https://github.com/ggerganov/llama.cpp/commit/4d4d2366fc9c54d4a275065cfe9299c6cf7c5b78#diff-db4ed1f953cd7f07c37dfe2d725ac7f8ccae3fbb822cebd01662682f77e6ffe7R1284
- https://github.com/ggerganov/llama.cpp/commit/e76627bcce9f77adb6034cb127b7ec93d4287b69
- https://github.com/ggerganov/llama.cpp/commit/ff5a3f0c09dfa0a8e0bf76d1748df5c6dee0e8ff#diff-db4ed1f953cd7f07c37dfe2d725ac7f8ccae3fbb822cebd01662682f77e6ffe7R338
BPE tokenizer implementations keep me up at night.
Rant aside, the BpeVocab is assuming the huggingface "fast" or "slow" tokenizer, but this is neither.
It should be noted that Llama 1 and Llama 2 used sentencepiece models. Llama-3 is using a tiktoken implementation and released it with a plaintext BPE "model" file.
17:51:49 | /mnt/valerie/models/meta-llama
λ file Meta-Llama-3-8B-Instruct/tokenizer.model
Meta-Llama-3-8B-Instruct/tokenizer.model: ASCII text
17:52:05 | /mnt/valerie/models/meta-llama
λ file /mnt/scsm/models/facebook/llama-2/llama-2-7b/tokenizer.model
/mnt/scsm/models/facebook/llama-2/llama-2-7b/tokenizer.model: data
cc @dranger003 - I really appreciated your ppl chart visual + measured ppl gap table for different quantization types for CommandR+. Do you think you would be willing to recreate those comparisons on L3 70b (base or Instruct, preferably base?) Thanks
@teleprint-me Are you saying that it's a happy coincidence that the current llama.cpp implementation happens to tokenize correctly or there exists character sequences out there that will be tokenized incorrectly?
Does anyone have convert instructions that work - I'm trying both Meta and HF models using this PR and none of the convert scripts work:
$ python3.11 convert.py ~/Data/llama3/Meta-Llama-3-8B/ --outfile ./models/llama-8b-v3/ggml-model-f16.gguf --outtype f16 --vocab-type bpe
FileNotFoundError: Could not find a tokenizer matching any of ['bpe']
$ python3.11 convert-hf-to-gguf.py ~/Data/huggingface/Meta-Llama-3-8B/ --outfile ./models/llama-8b-v3/ggml-model-f16.gguf --outtype f16
FileNotFoundError: File not found: /Users/ggerganov/Data/huggingface/Meta-Llama-3-8B/tokenizer.model
I see a few other people reporting the same problems. Those who succeeded - what were the necessary changes?
@ggerganov Try --vocab-type bpe with convert-hf-to-gguf.py, that worked for me
@ddh0 The convert-hf-to-gguf.py script does not support the --vocab-type argument:
$ python3.11 convert-hf-to-gguf.py ~/Data/huggingface/Meta-Llama-3-8B/ --outfile ./models/llama-8b-v3/ggml-model-f16.gguf --outtype f16 --vocab-type bpe
usage: convert-hf-to-gguf.py [-h] [--vocab-only] [--awq-path AWQ_PATH] [--outfile OUTFILE] [--outtype {f32,f16}] [--bigendian] [--use-temp-file] model
convert-hf-to-gguf.py: error: unrecognized arguments: --vocab-type bpe
@ggerganov These are working on my end.
convert.py works using master and this PR:
python convert.py /models/hub/Meta-Llama-3-8B/ --outfile /models/meta-llama/ggml-meta-llama-3-8b-f16.gguf --vocab-type bpe --outtype f16
convert-hf-to-gguf.py only works using this PR:
python convert-hf-to-gguf.py /models/hub/Meta-Llama-3-8B/ --outfile /models/meta-llama/ggml-meta-llama-3-8b-f16.gguf
It does not work on Mac OS:
$ ▶ python3.11 convert.py ~/Data/llama3/Meta-Llama-3-8B/ --outfile ./models/llama-8b-v3/ggml-model-f16.gguf --vocab-type bpe --outtype f16
Loading model file /Users/ggerganov/Data/llama3/Meta-Llama-3-8B/consolidated.00.pth
params = Params(n_vocab=128256, n_embd=4096, n_layer=32, n_ctx=4096, n_ff=14336, n_head=32, n_head_kv=8, n_experts=None, n_experts_used=None, f_norm_eps=1e-05, rope_scaling_type=None, f_rope_freq_base=500000.0, f_rope_scale=None, n_orig_ctx=None, rope_finetuned=None, ftype=<GGMLFileType.MostlyF16: 1>, path_model=PosixPath('/Users/ggerganov/Data/llama3/Meta-Llama-3-8B'))
Traceback (most recent call last):
File "/Users/ggerganov/development/github/llama.cpp/convert.py", line 1548, in <module>
main()
File "/Users/ggerganov/development/github/llama.cpp/convert.py", line 1515, in main
vocab, special_vocab = vocab_factory.load_vocab(vocab_types, model_parent_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ggerganov/development/github/llama.cpp/convert.py", line 1417, in load_vocab
vocab = self._create_vocab_by_path(vocab_types)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/ggerganov/development/github/llama.cpp/convert.py", line 1407, in _create_vocab_by_path
raise FileNotFoundError(f"Could not find a tokenizer matching any of {vocab_types}")
FileNotFoundError: Could not find a tokenizer matching any of ['bpe']
It could be something wrong with my Python setup though - somehow I have 2 versions now: 3.11 and 3.12. Quite messy - all kinds of packages and versions, I'm a bit lost at this point
Did anyone got this running on Mac?
Sorry, forgot to mention I am unable to convert the Meta weights (i.e. pth), just the HF weights are working.
@dranger003 Does the gguf model generated by conver-hf-to-gguf.py of this PR work on your end? I used Q5_K_M on my side and the text generation was not correct:
- Input
"messages": [
{
"role": "system",
"content": "You are a helpful, respectful and honest assistant. Always answer as short as possible, while being safe."
},
{
"role": "user",
"content": "What is captial of France?"
}
]
- Generation:
"message": {
"role": "assistant",
"content": "Paris.assistant\n\nThat's correct! The capital of France is indeed Paris.assistant\n\nCorrect again!assistant\n\nYou're on a roll!assistant\n\nHehe, thanks!assistant\n\nYou're welcome!assistant\n\nYou're welcome back!assistant\n\nHa ha, nice one!assistant\n\nBack atcha!assistant\n\nWe're having fun!assistant"
}
The Q5_K_M model is here.
SHA256: 2a50fd6d990f523bcec82460b7f78cc4ac1cb927c004c04e7f843bcf9f21a260
@ggerganov The convert-hf-to-gguf.py of this PR works on my side. Before running the python script, use pip install -e ./gguf-py/. to update the local gguf package. For your convenience, I list the installed python package below:
(facet) (base) azureuser@sam-llm:/data/sam/models/second-state$ python --version
Python 3.11.8
(facet) (base) azureuser@sam-llm:/data/sam/models/second-state$ pip list installed
Package Version Editable project location
------------------------ ---------- -------------------------------------------
certifi 2023.7.22
charset-normalizer 3.3.2
einops 0.7.0
filelock 3.13.1
fsspec 2023.10.0
gguf 0.9.0 /home/azureuser/workspace/llama.cpp/gguf-py
gitdb 4.0.11
GitPython 3.1.40
huggingface-hub 0.22.2
idna 3.4
Jinja2 3.1.2
MarkupSafe 2.1.3
mpmath 1.3.0
networkx 3.2.1
numpy 1.24.4
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 8.9.2.26
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-nccl-cu12 2.18.1
nvidia-nvjitlink-cu12 12.4.127
nvidia-nvtx-cu12 12.1.105
packaging 23.2
pip 23.3.1
protobuf 4.25.0
PyYAML 6.0.1
regex 2023.10.3
requests 2.31.0
safetensors 0.4.3
sentencepiece 0.1.99
setuptools 68.2.2
smmap 5.0.1
sympy 1.12
tiktoken 0.5.2
tokenizers 0.19.1
torch 2.1.2
tqdm 4.66.1
transformers 4.40.0
triton 2.1.0
typing_extensions 4.8.0
urllib3 2.1.0
wheel 0.41.2