Commit
•
7886788
1
Parent(s):
96d5c62
initial release
Browse files- README.md +30 -0
- config.json +377 -0
- maker.sh +141 -0
- merges.txt +0 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +491 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +43 -0
- upos.py +77 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- "lzh"
|
| 4 |
+
tags:
|
| 5 |
+
- "classical chinese"
|
| 6 |
+
- "literary chinese"
|
| 7 |
+
- "ancient chinese"
|
| 8 |
+
- "token-classification"
|
| 9 |
+
- "pos"
|
| 10 |
+
- "dependency-parsing"
|
| 11 |
+
datasets:
|
| 12 |
+
- "universal_dependencies"
|
| 13 |
+
license: "apache-2.0"
|
| 14 |
+
pipeline_tag: "token-classification"
|
| 15 |
+
widget:
|
| 16 |
+
- text: "子曰學而時習之不亦説乎有朋自遠方來不亦樂乎人不知而不慍不亦君子乎"
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Xunzi-Qwen1.5-4B-upos
|
| 20 |
+
|
| 21 |
+
## Model Description
|
| 22 |
+
|
| 23 |
+
This is a Qwen1.5 model pre-trained on Classical Chinese texts for POS-tagging, derived from [Xunzi-Qwen1.5-4B](https://www.modelscope.cn/models/Xunzillm4cc/Xunzi-Qwen1.5-4B). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
|
| 24 |
+
|
| 25 |
+
## How to Use
|
| 26 |
+
|
| 27 |
+
```py
|
| 28 |
+
from transformers import pipeline
|
| 29 |
+
nlp=pipeline("upos","KoichiYasuoka/Xunzi-Qwen1.5-4B-upos",trust_remote_code=True,aggregation_strategy="simple")
|
| 30 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,377 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoModelForTokenClassification": "upos.Qwen2ForTokenClassification"
|
| 8 |
+
},
|
| 9 |
+
"bos_token_id": 151643,
|
| 10 |
+
"custom_pipelines": {
|
| 11 |
+
"upos": {
|
| 12 |
+
"impl": "upos.BellmanFordTokenClassificationPipeline",
|
| 13 |
+
"pt": "AutoModelForTokenClassification"
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"eos_token_id": 151643,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 2560,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "ADP",
|
| 21 |
+
"1": "ADP|Degree=Equ",
|
| 22 |
+
"2": "ADV",
|
| 23 |
+
"3": "ADV|AdvType=Cau",
|
| 24 |
+
"4": "ADV|AdvType=Deg|Degree=Cmp",
|
| 25 |
+
"5": "ADV|AdvType=Deg|Degree=Pos",
|
| 26 |
+
"6": "ADV|AdvType=Deg|Degree=Sup",
|
| 27 |
+
"7": "ADV|AdvType=Tim",
|
| 28 |
+
"8": "ADV|AdvType=Tim|Aspect=Perf",
|
| 29 |
+
"9": "ADV|AdvType=Tim|Tense=Fut",
|
| 30 |
+
"10": "ADV|AdvType=Tim|Tense=Past",
|
| 31 |
+
"11": "ADV|AdvType=Tim|Tense=Pres",
|
| 32 |
+
"12": "ADV|Degree=Equ|VerbForm=Conv",
|
| 33 |
+
"13": "ADV|Degree=Pos|VerbForm=Conv",
|
| 34 |
+
"14": "ADV|Polarity=Neg",
|
| 35 |
+
"15": "ADV|Polarity=Neg|VerbForm=Conv",
|
| 36 |
+
"16": "ADV|VerbForm=Conv",
|
| 37 |
+
"17": "AUX|Mood=Des",
|
| 38 |
+
"18": "AUX|Mood=Nec",
|
| 39 |
+
"19": "AUX|Mood=Pot",
|
| 40 |
+
"20": "AUX|VerbType=Cop",
|
| 41 |
+
"21": "AUX|Voice=Pass",
|
| 42 |
+
"22": "B-ADP",
|
| 43 |
+
"23": "B-ADP|Degree=Equ",
|
| 44 |
+
"24": "B-ADV",
|
| 45 |
+
"25": "B-ADV|AdvType=Cau",
|
| 46 |
+
"26": "B-ADV|AdvType=Deg|Degree=Cmp",
|
| 47 |
+
"27": "B-ADV|AdvType=Deg|Degree=Pos",
|
| 48 |
+
"28": "B-ADV|AdvType=Deg|Degree=Sup",
|
| 49 |
+
"29": "B-ADV|AdvType=Tim",
|
| 50 |
+
"30": "B-ADV|AdvType=Tim|Aspect=Perf",
|
| 51 |
+
"31": "B-ADV|AdvType=Tim|Tense=Fut",
|
| 52 |
+
"32": "B-ADV|AdvType=Tim|Tense=Past",
|
| 53 |
+
"33": "B-ADV|AdvType=Tim|Tense=Pres",
|
| 54 |
+
"34": "B-ADV|Degree=Equ|VerbForm=Conv",
|
| 55 |
+
"35": "B-ADV|Degree=Pos|VerbForm=Conv",
|
| 56 |
+
"36": "B-ADV|Polarity=Neg",
|
| 57 |
+
"37": "B-ADV|Polarity=Neg|VerbForm=Conv",
|
| 58 |
+
"38": "B-ADV|VerbForm=Conv",
|
| 59 |
+
"39": "B-AUX|Mood=Des",
|
| 60 |
+
"40": "B-AUX|Mood=Nec",
|
| 61 |
+
"41": "B-AUX|Mood=Pot",
|
| 62 |
+
"42": "B-AUX|VerbType=Cop",
|
| 63 |
+
"43": "B-AUX|Voice=Pass",
|
| 64 |
+
"44": "B-CCONJ",
|
| 65 |
+
"45": "B-INTJ",
|
| 66 |
+
"46": "B-NOUN",
|
| 67 |
+
"47": "B-NOUN|Case=Loc",
|
| 68 |
+
"48": "B-NOUN|Case=Tem",
|
| 69 |
+
"49": "B-NOUN|Degree=Pos",
|
| 70 |
+
"50": "B-NOUN|NounType=Clf",
|
| 71 |
+
"51": "B-NUM",
|
| 72 |
+
"52": "B-NUM|NumType=Ord",
|
| 73 |
+
"53": "B-PART",
|
| 74 |
+
"54": "B-PRON|Person=1|PronType=Prs",
|
| 75 |
+
"55": "B-PRON|Person=2|PronType=Prs",
|
| 76 |
+
"56": "B-PRON|Person=3|PronType=Prs",
|
| 77 |
+
"57": "B-PRON|PronType=Dem",
|
| 78 |
+
"58": "B-PRON|PronType=Int",
|
| 79 |
+
"59": "B-PRON|PronType=Prs",
|
| 80 |
+
"60": "B-PRON|PronType=Prs|Reflex=Yes",
|
| 81 |
+
"61": "B-PROPN",
|
| 82 |
+
"62": "B-PROPN|Case=Loc|NameType=Geo",
|
| 83 |
+
"63": "B-PROPN|Case=Loc|NameType=Nat",
|
| 84 |
+
"64": "B-PROPN|NameType=Giv",
|
| 85 |
+
"65": "B-PROPN|NameType=Prs",
|
| 86 |
+
"66": "B-PROPN|NameType=Sur",
|
| 87 |
+
"67": "B-PUNCT",
|
| 88 |
+
"68": "B-SCONJ",
|
| 89 |
+
"69": "B-SYM",
|
| 90 |
+
"70": "B-VERB",
|
| 91 |
+
"71": "B-VERB|Degree=Equ",
|
| 92 |
+
"72": "B-VERB|Degree=Equ|VerbForm=Part",
|
| 93 |
+
"73": "B-VERB|Degree=Pos",
|
| 94 |
+
"74": "B-VERB|Degree=Pos|VerbForm=Part",
|
| 95 |
+
"75": "B-VERB|Polarity=Neg",
|
| 96 |
+
"76": "B-VERB|Polarity=Neg|VerbForm=Part",
|
| 97 |
+
"77": "B-VERB|VerbForm=Part",
|
| 98 |
+
"78": "CCONJ",
|
| 99 |
+
"79": "I-ADP",
|
| 100 |
+
"80": "I-ADP|Degree=Equ",
|
| 101 |
+
"81": "I-ADV",
|
| 102 |
+
"82": "I-ADV|AdvType=Cau",
|
| 103 |
+
"83": "I-ADV|AdvType=Deg|Degree=Cmp",
|
| 104 |
+
"84": "I-ADV|AdvType=Deg|Degree=Pos",
|
| 105 |
+
"85": "I-ADV|AdvType=Deg|Degree=Sup",
|
| 106 |
+
"86": "I-ADV|AdvType=Tim",
|
| 107 |
+
"87": "I-ADV|AdvType=Tim|Aspect=Perf",
|
| 108 |
+
"88": "I-ADV|AdvType=Tim|Tense=Fut",
|
| 109 |
+
"89": "I-ADV|AdvType=Tim|Tense=Past",
|
| 110 |
+
"90": "I-ADV|AdvType=Tim|Tense=Pres",
|
| 111 |
+
"91": "I-ADV|Degree=Equ|VerbForm=Conv",
|
| 112 |
+
"92": "I-ADV|Degree=Pos|VerbForm=Conv",
|
| 113 |
+
"93": "I-ADV|Polarity=Neg",
|
| 114 |
+
"94": "I-ADV|Polarity=Neg|VerbForm=Conv",
|
| 115 |
+
"95": "I-ADV|VerbForm=Conv",
|
| 116 |
+
"96": "I-AUX|Mood=Des",
|
| 117 |
+
"97": "I-AUX|Mood=Nec",
|
| 118 |
+
"98": "I-AUX|Mood=Pot",
|
| 119 |
+
"99": "I-AUX|VerbType=Cop",
|
| 120 |
+
"100": "I-AUX|Voice=Pass",
|
| 121 |
+
"101": "I-CCONJ",
|
| 122 |
+
"102": "I-INTJ",
|
| 123 |
+
"103": "I-NOUN",
|
| 124 |
+
"104": "I-NOUN|Case=Loc",
|
| 125 |
+
"105": "I-NOUN|Case=Tem",
|
| 126 |
+
"106": "I-NOUN|Degree=Pos",
|
| 127 |
+
"107": "I-NOUN|NounType=Clf",
|
| 128 |
+
"108": "I-NUM",
|
| 129 |
+
"109": "I-NUM|NumType=Ord",
|
| 130 |
+
"110": "I-PART",
|
| 131 |
+
"111": "I-PRON|Person=1|PronType=Prs",
|
| 132 |
+
"112": "I-PRON|Person=2|PronType=Prs",
|
| 133 |
+
"113": "I-PRON|Person=3|PronType=Prs",
|
| 134 |
+
"114": "I-PRON|PronType=Dem",
|
| 135 |
+
"115": "I-PRON|PronType=Int",
|
| 136 |
+
"116": "I-PRON|PronType=Prs",
|
| 137 |
+
"117": "I-PRON|PronType=Prs|Reflex=Yes",
|
| 138 |
+
"118": "I-PROPN",
|
| 139 |
+
"119": "I-PROPN|Case=Loc|NameType=Geo",
|
| 140 |
+
"120": "I-PROPN|Case=Loc|NameType=Nat",
|
| 141 |
+
"121": "I-PROPN|NameType=Giv",
|
| 142 |
+
"122": "I-PROPN|NameType=Prs",
|
| 143 |
+
"123": "I-PROPN|NameType=Sur",
|
| 144 |
+
"124": "I-PUNCT",
|
| 145 |
+
"125": "I-SCONJ",
|
| 146 |
+
"126": "I-SYM",
|
| 147 |
+
"127": "I-VERB",
|
| 148 |
+
"128": "I-VERB|Degree=Equ",
|
| 149 |
+
"129": "I-VERB|Degree=Equ|VerbForm=Part",
|
| 150 |
+
"130": "I-VERB|Degree=Pos",
|
| 151 |
+
"131": "I-VERB|Degree=Pos|VerbForm=Part",
|
| 152 |
+
"132": "I-VERB|Polarity=Neg",
|
| 153 |
+
"133": "I-VERB|Polarity=Neg|VerbForm=Part",
|
| 154 |
+
"134": "I-VERB|VerbForm=Part",
|
| 155 |
+
"135": "INTJ",
|
| 156 |
+
"136": "NOUN",
|
| 157 |
+
"137": "NOUN|Case=Loc",
|
| 158 |
+
"138": "NOUN|Case=Tem",
|
| 159 |
+
"139": "NOUN|Degree=Pos",
|
| 160 |
+
"140": "NOUN|NounType=Clf",
|
| 161 |
+
"141": "NUM",
|
| 162 |
+
"142": "NUM|NumType=Ord",
|
| 163 |
+
"143": "PART",
|
| 164 |
+
"144": "PRON|Person=1|PronType=Prs",
|
| 165 |
+
"145": "PRON|Person=2|PronType=Prs",
|
| 166 |
+
"146": "PRON|Person=3|PronType=Prs",
|
| 167 |
+
"147": "PRON|PronType=Dem",
|
| 168 |
+
"148": "PRON|PronType=Int",
|
| 169 |
+
"149": "PRON|PronType=Prs",
|
| 170 |
+
"150": "PRON|PronType=Prs|Reflex=Yes",
|
| 171 |
+
"151": "PROPN",
|
| 172 |
+
"152": "PROPN|Case=Loc|NameType=Geo",
|
| 173 |
+
"153": "PROPN|Case=Loc|NameType=Nat",
|
| 174 |
+
"154": "PROPN|NameType=Giv",
|
| 175 |
+
"155": "PROPN|NameType=Prs",
|
| 176 |
+
"156": "PROPN|NameType=Sur",
|
| 177 |
+
"157": "PUNCT",
|
| 178 |
+
"158": "SCONJ",
|
| 179 |
+
"159": "SYM",
|
| 180 |
+
"160": "VERB",
|
| 181 |
+
"161": "VERB|Degree=Equ",
|
| 182 |
+
"162": "VERB|Degree=Equ|VerbForm=Part",
|
| 183 |
+
"163": "VERB|Degree=Pos",
|
| 184 |
+
"164": "VERB|Degree=Pos|VerbForm=Part",
|
| 185 |
+
"165": "VERB|Polarity=Neg",
|
| 186 |
+
"166": "VERB|Polarity=Neg|VerbForm=Part",
|
| 187 |
+
"167": "VERB|VerbForm=Part"
|
| 188 |
+
},
|
| 189 |
+
"initializer_range": 0.02,
|
| 190 |
+
"intermediate_size": 6912,
|
| 191 |
+
"label2id": {
|
| 192 |
+
"ADP": 0,
|
| 193 |
+
"ADP|Degree=Equ": 1,
|
| 194 |
+
"ADV": 2,
|
| 195 |
+
"ADV|AdvType=Cau": 3,
|
| 196 |
+
"ADV|AdvType=Deg|Degree=Cmp": 4,
|
| 197 |
+
"ADV|AdvType=Deg|Degree=Pos": 5,
|
| 198 |
+
"ADV|AdvType=Deg|Degree=Sup": 6,
|
| 199 |
+
"ADV|AdvType=Tim": 7,
|
| 200 |
+
"ADV|AdvType=Tim|Aspect=Perf": 8,
|
| 201 |
+
"ADV|AdvType=Tim|Tense=Fut": 9,
|
| 202 |
+
"ADV|AdvType=Tim|Tense=Past": 10,
|
| 203 |
+
"ADV|AdvType=Tim|Tense=Pres": 11,
|
| 204 |
+
"ADV|Degree=Equ|VerbForm=Conv": 12,
|
| 205 |
+
"ADV|Degree=Pos|VerbForm=Conv": 13,
|
| 206 |
+
"ADV|Polarity=Neg": 14,
|
| 207 |
+
"ADV|Polarity=Neg|VerbForm=Conv": 15,
|
| 208 |
+
"ADV|VerbForm=Conv": 16,
|
| 209 |
+
"AUX|Mood=Des": 17,
|
| 210 |
+
"AUX|Mood=Nec": 18,
|
| 211 |
+
"AUX|Mood=Pot": 19,
|
| 212 |
+
"AUX|VerbType=Cop": 20,
|
| 213 |
+
"AUX|Voice=Pass": 21,
|
| 214 |
+
"B-ADP": 22,
|
| 215 |
+
"B-ADP|Degree=Equ": 23,
|
| 216 |
+
"B-ADV": 24,
|
| 217 |
+
"B-ADV|AdvType=Cau": 25,
|
| 218 |
+
"B-ADV|AdvType=Deg|Degree=Cmp": 26,
|
| 219 |
+
"B-ADV|AdvType=Deg|Degree=Pos": 27,
|
| 220 |
+
"B-ADV|AdvType=Deg|Degree=Sup": 28,
|
| 221 |
+
"B-ADV|AdvType=Tim": 29,
|
| 222 |
+
"B-ADV|AdvType=Tim|Aspect=Perf": 30,
|
| 223 |
+
"B-ADV|AdvType=Tim|Tense=Fut": 31,
|
| 224 |
+
"B-ADV|AdvType=Tim|Tense=Past": 32,
|
| 225 |
+
"B-ADV|AdvType=Tim|Tense=Pres": 33,
|
| 226 |
+
"B-ADV|Degree=Equ|VerbForm=Conv": 34,
|
| 227 |
+
"B-ADV|Degree=Pos|VerbForm=Conv": 35,
|
| 228 |
+
"B-ADV|Polarity=Neg": 36,
|
| 229 |
+
"B-ADV|Polarity=Neg|VerbForm=Conv": 37,
|
| 230 |
+
"B-ADV|VerbForm=Conv": 38,
|
| 231 |
+
"B-AUX|Mood=Des": 39,
|
| 232 |
+
"B-AUX|Mood=Nec": 40,
|
| 233 |
+
"B-AUX|Mood=Pot": 41,
|
| 234 |
+
"B-AUX|VerbType=Cop": 42,
|
| 235 |
+
"B-AUX|Voice=Pass": 43,
|
| 236 |
+
"B-CCONJ": 44,
|
| 237 |
+
"B-INTJ": 45,
|
| 238 |
+
"B-NOUN": 46,
|
| 239 |
+
"B-NOUN|Case=Loc": 47,
|
| 240 |
+
"B-NOUN|Case=Tem": 48,
|
| 241 |
+
"B-NOUN|Degree=Pos": 49,
|
| 242 |
+
"B-NOUN|NounType=Clf": 50,
|
| 243 |
+
"B-NUM": 51,
|
| 244 |
+
"B-NUM|NumType=Ord": 52,
|
| 245 |
+
"B-PART": 53,
|
| 246 |
+
"B-PRON|Person=1|PronType=Prs": 54,
|
| 247 |
+
"B-PRON|Person=2|PronType=Prs": 55,
|
| 248 |
+
"B-PRON|Person=3|PronType=Prs": 56,
|
| 249 |
+
"B-PRON|PronType=Dem": 57,
|
| 250 |
+
"B-PRON|PronType=Int": 58,
|
| 251 |
+
"B-PRON|PronType=Prs": 59,
|
| 252 |
+
"B-PRON|PronType=Prs|Reflex=Yes": 60,
|
| 253 |
+
"B-PROPN": 61,
|
| 254 |
+
"B-PROPN|Case=Loc|NameType=Geo": 62,
|
| 255 |
+
"B-PROPN|Case=Loc|NameType=Nat": 63,
|
| 256 |
+
"B-PROPN|NameType=Giv": 64,
|
| 257 |
+
"B-PROPN|NameType=Prs": 65,
|
| 258 |
+
"B-PROPN|NameType=Sur": 66,
|
| 259 |
+
"B-PUNCT": 67,
|
| 260 |
+
"B-SCONJ": 68,
|
| 261 |
+
"B-SYM": 69,
|
| 262 |
+
"B-VERB": 70,
|
| 263 |
+
"B-VERB|Degree=Equ": 71,
|
| 264 |
+
"B-VERB|Degree=Equ|VerbForm=Part": 72,
|
| 265 |
+
"B-VERB|Degree=Pos": 73,
|
| 266 |
+
"B-VERB|Degree=Pos|VerbForm=Part": 74,
|
| 267 |
+
"B-VERB|Polarity=Neg": 75,
|
| 268 |
+
"B-VERB|Polarity=Neg|VerbForm=Part": 76,
|
| 269 |
+
"B-VERB|VerbForm=Part": 77,
|
| 270 |
+
"CCONJ": 78,
|
| 271 |
+
"I-ADP": 79,
|
| 272 |
+
"I-ADP|Degree=Equ": 80,
|
| 273 |
+
"I-ADV": 81,
|
| 274 |
+
"I-ADV|AdvType=Cau": 82,
|
| 275 |
+
"I-ADV|AdvType=Deg|Degree=Cmp": 83,
|
| 276 |
+
"I-ADV|AdvType=Deg|Degree=Pos": 84,
|
| 277 |
+
"I-ADV|AdvType=Deg|Degree=Sup": 85,
|
| 278 |
+
"I-ADV|AdvType=Tim": 86,
|
| 279 |
+
"I-ADV|AdvType=Tim|Aspect=Perf": 87,
|
| 280 |
+
"I-ADV|AdvType=Tim|Tense=Fut": 88,
|
| 281 |
+
"I-ADV|AdvType=Tim|Tense=Past": 89,
|
| 282 |
+
"I-ADV|AdvType=Tim|Tense=Pres": 90,
|
| 283 |
+
"I-ADV|Degree=Equ|VerbForm=Conv": 91,
|
| 284 |
+
"I-ADV|Degree=Pos|VerbForm=Conv": 92,
|
| 285 |
+
"I-ADV|Polarity=Neg": 93,
|
| 286 |
+
"I-ADV|Polarity=Neg|VerbForm=Conv": 94,
|
| 287 |
+
"I-ADV|VerbForm=Conv": 95,
|
| 288 |
+
"I-AUX|Mood=Des": 96,
|
| 289 |
+
"I-AUX|Mood=Nec": 97,
|
| 290 |
+
"I-AUX|Mood=Pot": 98,
|
| 291 |
+
"I-AUX|VerbType=Cop": 99,
|
| 292 |
+
"I-AUX|Voice=Pass": 100,
|
| 293 |
+
"I-CCONJ": 101,
|
| 294 |
+
"I-INTJ": 102,
|
| 295 |
+
"I-NOUN": 103,
|
| 296 |
+
"I-NOUN|Case=Loc": 104,
|
| 297 |
+
"I-NOUN|Case=Tem": 105,
|
| 298 |
+
"I-NOUN|Degree=Pos": 106,
|
| 299 |
+
"I-NOUN|NounType=Clf": 107,
|
| 300 |
+
"I-NUM": 108,
|
| 301 |
+
"I-NUM|NumType=Ord": 109,
|
| 302 |
+
"I-PART": 110,
|
| 303 |
+
"I-PRON|Person=1|PronType=Prs": 111,
|
| 304 |
+
"I-PRON|Person=2|PronType=Prs": 112,
|
| 305 |
+
"I-PRON|Person=3|PronType=Prs": 113,
|
| 306 |
+
"I-PRON|PronType=Dem": 114,
|
| 307 |
+
"I-PRON|PronType=Int": 115,
|
| 308 |
+
"I-PRON|PronType=Prs": 116,
|
| 309 |
+
"I-PRON|PronType=Prs|Reflex=Yes": 117,
|
| 310 |
+
"I-PROPN": 118,
|
| 311 |
+
"I-PROPN|Case=Loc|NameType=Geo": 119,
|
| 312 |
+
"I-PROPN|Case=Loc|NameType=Nat": 120,
|
| 313 |
+
"I-PROPN|NameType=Giv": 121,
|
| 314 |
+
"I-PROPN|NameType=Prs": 122,
|
| 315 |
+
"I-PROPN|NameType=Sur": 123,
|
| 316 |
+
"I-PUNCT": 124,
|
| 317 |
+
"I-SCONJ": 125,
|
| 318 |
+
"I-SYM": 126,
|
| 319 |
+
"I-VERB": 127,
|
| 320 |
+
"I-VERB|Degree=Equ": 128,
|
| 321 |
+
"I-VERB|Degree=Equ|VerbForm=Part": 129,
|
| 322 |
+
"I-VERB|Degree=Pos": 130,
|
| 323 |
+
"I-VERB|Degree=Pos|VerbForm=Part": 131,
|
| 324 |
+
"I-VERB|Polarity=Neg": 132,
|
| 325 |
+
"I-VERB|Polarity=Neg|VerbForm=Part": 133,
|
| 326 |
+
"I-VERB|VerbForm=Part": 134,
|
| 327 |
+
"INTJ": 135,
|
| 328 |
+
"NOUN": 136,
|
| 329 |
+
"NOUN|Case=Loc": 137,
|
| 330 |
+
"NOUN|Case=Tem": 138,
|
| 331 |
+
"NOUN|Degree=Pos": 139,
|
| 332 |
+
"NOUN|NounType=Clf": 140,
|
| 333 |
+
"NUM": 141,
|
| 334 |
+
"NUM|NumType=Ord": 142,
|
| 335 |
+
"PART": 143,
|
| 336 |
+
"PRON|Person=1|PronType=Prs": 144,
|
| 337 |
+
"PRON|Person=2|PronType=Prs": 145,
|
| 338 |
+
"PRON|Person=3|PronType=Prs": 146,
|
| 339 |
+
"PRON|PronType=Dem": 147,
|
| 340 |
+
"PRON|PronType=Int": 148,
|
| 341 |
+
"PRON|PronType=Prs": 149,
|
| 342 |
+
"PRON|PronType=Prs|Reflex=Yes": 150,
|
| 343 |
+
"PROPN": 151,
|
| 344 |
+
"PROPN|Case=Loc|NameType=Geo": 152,
|
| 345 |
+
"PROPN|Case=Loc|NameType=Nat": 153,
|
| 346 |
+
"PROPN|NameType=Giv": 154,
|
| 347 |
+
"PROPN|NameType=Prs": 155,
|
| 348 |
+
"PROPN|NameType=Sur": 156,
|
| 349 |
+
"PUNCT": 157,
|
| 350 |
+
"SCONJ": 158,
|
| 351 |
+
"SYM": 159,
|
| 352 |
+
"VERB": 160,
|
| 353 |
+
"VERB|Degree=Equ": 161,
|
| 354 |
+
"VERB|Degree=Equ|VerbForm=Part": 162,
|
| 355 |
+
"VERB|Degree=Pos": 163,
|
| 356 |
+
"VERB|Degree=Pos|VerbForm=Part": 164,
|
| 357 |
+
"VERB|Polarity=Neg": 165,
|
| 358 |
+
"VERB|Polarity=Neg|VerbForm=Part": 166,
|
| 359 |
+
"VERB|VerbForm=Part": 167
|
| 360 |
+
},
|
| 361 |
+
"max_position_embeddings": 32768,
|
| 362 |
+
"max_window_layers": 21,
|
| 363 |
+
"model_type": "qwen2",
|
| 364 |
+
"num_attention_heads": 20,
|
| 365 |
+
"num_hidden_layers": 40,
|
| 366 |
+
"num_key_value_heads": 20,
|
| 367 |
+
"rms_norm_eps": 1e-06,
|
| 368 |
+
"rope_theta": 5000000.0,
|
| 369 |
+
"sliding_window": 32768,
|
| 370 |
+
"tie_word_embeddings": false,
|
| 371 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 372 |
+
"torch_dtype": "float32",
|
| 373 |
+
"transformers_version": "4.41.2",
|
| 374 |
+
"use_cache": false,
|
| 375 |
+
"use_sliding_window": false,
|
| 376 |
+
"vocab_size": 151936
|
| 377 |
+
}
|
maker.sh
ADDED
|
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#! /bin/sh
|
| 2 |
+
S=Xunzi-Qwen1.5-4B
|
| 3 |
+
U=UD_Classical_Chinese-Kyoto
|
| 4 |
+
test -d $U || git clone --depth=1 https://github.com/UniversalDependencies/$U
|
| 5 |
+
for F in train dev test
|
| 6 |
+
do cp $U/*-$F.conllu $F.conllu
|
| 7 |
+
done
|
| 8 |
+
test -d $S || git clone --depth=1 https://www.modelscope.cn/Xunzillm4cc/$S.git
|
| 9 |
+
|
| 10 |
+
TMP=./maker$$.py
|
| 11 |
+
( echo '#! /usr/bin/env deepspeed'
|
| 12 |
+
echo 'src="'$S'"'
|
| 13 |
+
echo 'tgt="KoichiYasuoka/'$S'-upos"'
|
| 14 |
+
) > $TMP
|
| 15 |
+
cat << 'EOF' >> $TMP
|
| 16 |
+
from transformers import AutoTokenizer,Qwen2Model,Qwen2PreTrainedModel,AutoConfig,DataCollatorForTokenClassification,TrainingArguments,Trainer
|
| 17 |
+
from transformers.modeling_outputs import TokenClassifierOutput
|
| 18 |
+
|
| 19 |
+
class Qwen2ForTokenClassification(Qwen2PreTrainedModel):
|
| 20 |
+
def __init__(self,config):
|
| 21 |
+
from torch import nn
|
| 22 |
+
super().__init__(config)
|
| 23 |
+
self.num_labels=config.num_labels
|
| 24 |
+
self.model=Qwen2Model(config)
|
| 25 |
+
if getattr(config,"classifier_dropout",None) is not None:
|
| 26 |
+
classifier_dropout=config.classifier_dropout
|
| 27 |
+
elif getattr(config,"hidden_dropout",None) is not None:
|
| 28 |
+
classifier_dropout=config.hidden_dropout
|
| 29 |
+
else:
|
| 30 |
+
classifier_dropout=0.1
|
| 31 |
+
self.dropout=nn.Dropout(classifier_dropout)
|
| 32 |
+
self.score=nn.Linear(config.hidden_size,config.num_labels)
|
| 33 |
+
self.post_init()
|
| 34 |
+
def get_input_embeddings(self):
|
| 35 |
+
return self.model.embed_tokens
|
| 36 |
+
def set_input_embeddings(self,value):
|
| 37 |
+
self.model.embed_tokens=value
|
| 38 |
+
def forward(self,input_ids=None,past_key_values=None,attention_mask=None,position_ids=None,inputs_embeds=None,labels=None,use_cache=None,output_attentions=None,output_hidden_states=None,return_dict=None):
|
| 39 |
+
return_dict=return_dict if return_dict is not None else self.config.use_return_dict
|
| 40 |
+
outputs=self.model(input_ids,past_key_values=past_key_values,attention_mask=attention_mask,position_ids=position_ids,inputs_embeds=inputs_embeds,use_cache=use_cache,output_attentions=output_attentions,output_hidden_states=output_hidden_states,return_dict=return_dict)
|
| 41 |
+
sequence_output=outputs[0]
|
| 42 |
+
sequence_output=self.dropout(sequence_output)
|
| 43 |
+
logits=self.score(sequence_output)
|
| 44 |
+
loss=None
|
| 45 |
+
if labels is not None:
|
| 46 |
+
from torch import nn
|
| 47 |
+
loss_fct=nn.CrossEntropyLoss()
|
| 48 |
+
loss=loss_fct(logits.view(-1,self.num_labels),labels.view(-1))
|
| 49 |
+
if not return_dict:
|
| 50 |
+
output=(logits,)+outputs[2:]
|
| 51 |
+
return ((loss,)+output) if loss is not None else output
|
| 52 |
+
return TokenClassifierOutput(loss=loss,logits=logits,hidden_states=outputs.hidden_states,attentions=outputs.attentions)
|
| 53 |
+
|
| 54 |
+
class UPOSFileDataset(object):
|
| 55 |
+
def __init__(self,conllu,tokenizer):
|
| 56 |
+
self.conllu=open(conllu,"r",encoding="utf-8")
|
| 57 |
+
self.tokenizer=tokenizer
|
| 58 |
+
self.seeks=[0]
|
| 59 |
+
self.multiword={}
|
| 60 |
+
label=set(["SYM"])
|
| 61 |
+
s=self.conllu.readline()
|
| 62 |
+
while s!="":
|
| 63 |
+
if s=="\n":
|
| 64 |
+
self.seeks.append(self.conllu.tell())
|
| 65 |
+
else:
|
| 66 |
+
w=s.split("\t")
|
| 67 |
+
if len(w)==10:
|
| 68 |
+
if w[0].isdecimal():
|
| 69 |
+
label.add(w[3] if w[5]=="_" else w[3]+"|"+w[5])
|
| 70 |
+
elif w[0].find("-")>0:
|
| 71 |
+
t=w[0].split("-")
|
| 72 |
+
f,j,k=w[1],[],[]
|
| 73 |
+
for i in range(int(t[0]),int(t[1])+1):
|
| 74 |
+
w=self.conllu.readline().split("\t")
|
| 75 |
+
j.append(w[3] if w[5]=="_" else w[3]+"|"+w[5])
|
| 76 |
+
k.append(w[1])
|
| 77 |
+
p="+".join(j)
|
| 78 |
+
label.add(p)
|
| 79 |
+
if p in self.multiword:
|
| 80 |
+
self.multiword[p][f]=list(k)
|
| 81 |
+
else:
|
| 82 |
+
self.multiword[p]={f:list(k)}
|
| 83 |
+
s=self.conllu.readline()
|
| 84 |
+
lid={}
|
| 85 |
+
for i,l in enumerate(sorted(label)):
|
| 86 |
+
lid[l],lid["B-"+l],lid["I-"+l]=i*3,i*3+1,i*3+2
|
| 87 |
+
self.label2id=lid
|
| 88 |
+
def __call__(*args):
|
| 89 |
+
lid={l:i for i,l in enumerate(sorted(set(sum([list(t.label2id) for t in args],[]))))}
|
| 90 |
+
for t in args:
|
| 91 |
+
t.label2id=lid
|
| 92 |
+
return lid
|
| 93 |
+
def __del__(self):
|
| 94 |
+
self.conllu.close()
|
| 95 |
+
__len__=lambda self:len(self.seeks)-1
|
| 96 |
+
def __getitem__(self,i):
|
| 97 |
+
self.conllu.seek(self.seeks[i])
|
| 98 |
+
form,upos=[],[]
|
| 99 |
+
while self.conllu.tell()<self.seeks[i+1]:
|
| 100 |
+
w=self.conllu.readline().split("\t")
|
| 101 |
+
if len(w)==10:
|
| 102 |
+
form.append(w[1])
|
| 103 |
+
if w[0].isdecimal():
|
| 104 |
+
upos.append(w[3] if w[5]=="_" else w[3]+"|"+w[5])
|
| 105 |
+
elif w[0].find("-")>0:
|
| 106 |
+
t=w[0].split("-")
|
| 107 |
+
u=[]
|
| 108 |
+
for j in range(int(t[0]),int(t[1])+1):
|
| 109 |
+
k=self.conllu.readline().split("\t")
|
| 110 |
+
u.append(k[3] if k[5]=="_" else k[3]+"|"+k[5])
|
| 111 |
+
upos.append("+".join(u))
|
| 112 |
+
v=self.tokenizer(form,add_special_tokens=False)
|
| 113 |
+
i,u=[],[]
|
| 114 |
+
for j,(x,y) in enumerate(zip(v["input_ids"],upos)):
|
| 115 |
+
if x!=[]:
|
| 116 |
+
i+=x
|
| 117 |
+
u+=[y] if len(x)==1 else ["B-"+y]+["I-"+y]*(len(x)-1)
|
| 118 |
+
if len(i)<self.tokenizer.model_max_length-3:
|
| 119 |
+
ids=i
|
| 120 |
+
upos=u
|
| 121 |
+
else:
|
| 122 |
+
ids=i[0:self.tokenizer.model_max_length-2]
|
| 123 |
+
upos=u[0:self.tokenizer.model_max_length-2]
|
| 124 |
+
return {"input_ids":ids,"labels":[self.label2id[t] for t in upos]}
|
| 125 |
+
|
| 126 |
+
tkz=AutoTokenizer.from_pretrained(src)
|
| 127 |
+
trainDS=UPOSFileDataset("train.conllu",tkz)
|
| 128 |
+
devDS=UPOSFileDataset("dev.conllu",tkz)
|
| 129 |
+
testDS=UPOSFileDataset("test.conllu",tkz)
|
| 130 |
+
lid=trainDS(devDS,testDS)
|
| 131 |
+
cfg=AutoConfig.from_pretrained(src,num_labels=len(lid),label2id=lid,id2label={i:l for l,i in lid.items()},ignore_mismatched_sizes=True)
|
| 132 |
+
dsp={"fp16":{"enabled":"auto"},"optimizer":{"type":"AdamW"},"scheduler":{"type":"WarmupLR","params":{}},"train_batch_size":"auto","train_micro_batch_size_per_gpu":"auto","zero_optimization":{"stage":3,"offload_optimizer":{"device":"cpu","pin_memory":True},"offload_param":{"device":"cpu","pin_memory":True},"overlap_comm":True,"contiguous_gradients":True,"reduce_bucket_size":"auto","stage3_prefetch_bucket_size":"auto","stage3_param_persistence_threshold":"auto","stage3_gather_16bit_weights_on_model_save":True}}
|
| 133 |
+
arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=16,deepspeed=dsp,output_dir=tgt,overwrite_output_dir=True,save_total_limit=2,learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
|
| 134 |
+
trn=Trainer(args=arg,data_collator=DataCollatorForTokenClassification(tkz),model=Qwen2ForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True),train_dataset=trainDS)
|
| 135 |
+
trn.train()
|
| 136 |
+
trn.save_model(tgt)
|
| 137 |
+
tkz.save_pretrained(tgt)
|
| 138 |
+
EOF
|
| 139 |
+
chmod 755 $TMP
|
| 140 |
+
$TMP
|
| 141 |
+
exit
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model-00001-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5185783530ae8fed3b241173fa869e56fbdb2e134dc9154d20c08057c958db2
|
| 3 |
+
size 4974769352
|
pytorch_model-00002-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db08d2ff094e9c86a2bf683e97297da33031011d9e070cebf9b9ead1cad98ea4
|
| 3 |
+
size 4934433952
|
pytorch_model-00003-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ad91e73ed770e4a05528e3713b41a4c39b0796ebb5f68a3fb78cd13497b5c7e
|
| 3 |
+
size 4338334558
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,491 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14247373472
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 43 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 44 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 45 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 46 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 47 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 50 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 53 |
+
"model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 55 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 56 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 57 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 58 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 59 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 60 |
+
"model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 62 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 63 |
+
"model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 65 |
+
"model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 67 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 68 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 69 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 70 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 71 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 72 |
+
"model.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 74 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 75 |
+
"model.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 77 |
+
"model.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 79 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 84 |
+
"model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 86 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 117 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 118 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 119 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 120 |
+
"model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 122 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 123 |
+
"model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 125 |
+
"model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 129 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 130 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 131 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 132 |
+
"model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 134 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 135 |
+
"model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 137 |
+
"model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"model.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"model.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"model.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 152 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 153 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 154 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 155 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 156 |
+
"model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 158 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 159 |
+
"model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 161 |
+
"model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 163 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 164 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 165 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 166 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 167 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 168 |
+
"model.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 170 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 171 |
+
"model.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 173 |
+
"model.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 175 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 176 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 177 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 178 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 179 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 180 |
+
"model.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 182 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 183 |
+
"model.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 185 |
+
"model.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 187 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 188 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 189 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 190 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 191 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 192 |
+
"model.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 194 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 195 |
+
"model.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 197 |
+
"model.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 199 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 200 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 201 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 202 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 203 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 204 |
+
"model.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 206 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 207 |
+
"model.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 209 |
+
"model.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 211 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 212 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 213 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 214 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 215 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 216 |
+
"model.layers.24.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 218 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 219 |
+
"model.layers.24.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 221 |
+
"model.layers.24.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 223 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 224 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 225 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 226 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 227 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 228 |
+
"model.layers.25.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 230 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 231 |
+
"model.layers.25.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 233 |
+
"model.layers.25.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 235 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 236 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 237 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 238 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 239 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 240 |
+
"model.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 242 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 243 |
+
"model.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 245 |
+
"model.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 247 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 248 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 249 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 250 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 251 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 252 |
+
"model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 254 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 255 |
+
"model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 257 |
+
"model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 259 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 260 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 261 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 262 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 263 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 264 |
+
"model.layers.28.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 266 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 267 |
+
"model.layers.28.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 269 |
+
"model.layers.28.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 271 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 272 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 273 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 274 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 275 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 276 |
+
"model.layers.29.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 278 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 279 |
+
"model.layers.29.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 281 |
+
"model.layers.29.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 283 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 284 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 285 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 286 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 287 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 288 |
+
"model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 290 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 291 |
+
"model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 293 |
+
"model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 295 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 296 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 297 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 298 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 299 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 300 |
+
"model.layers.30.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 302 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 303 |
+
"model.layers.30.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 305 |
+
"model.layers.30.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 307 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 308 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 309 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 310 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 311 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 312 |
+
"model.layers.31.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 314 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 315 |
+
"model.layers.31.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 317 |
+
"model.layers.31.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 319 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 320 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 321 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 322 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 323 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 324 |
+
"model.layers.32.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 326 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 327 |
+
"model.layers.32.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 329 |
+
"model.layers.32.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 331 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 332 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 333 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 334 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 335 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 336 |
+
"model.layers.33.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 338 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 339 |
+
"model.layers.33.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 341 |
+
"model.layers.33.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 343 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 344 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 345 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 346 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 347 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 348 |
+
"model.layers.34.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 350 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 351 |
+
"model.layers.34.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 353 |
+
"model.layers.34.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 355 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 356 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 357 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 358 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 359 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 360 |
+
"model.layers.35.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 362 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 363 |
+
"model.layers.35.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 365 |
+
"model.layers.35.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 367 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 368 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 369 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 370 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 371 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 372 |
+
"model.layers.36.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 373 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 374 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 375 |
+
"model.layers.36.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 376 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 377 |
+
"model.layers.36.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 378 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 379 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 380 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 381 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 382 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 383 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 384 |
+
"model.layers.37.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 385 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 386 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 387 |
+
"model.layers.37.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 388 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 389 |
+
"model.layers.37.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 390 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 391 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 392 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 393 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 394 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 395 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 396 |
+
"model.layers.38.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 397 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 398 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 399 |
+
"model.layers.38.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 400 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 401 |
+
"model.layers.38.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 402 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 403 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 404 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 405 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 406 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 407 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 408 |
+
"model.layers.39.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 409 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 410 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 411 |
+
"model.layers.39.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 412 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 413 |
+
"model.layers.39.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 414 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 415 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 416 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 417 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 418 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 419 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 420 |
+
"model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 421 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 422 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 423 |
+
"model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 424 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 425 |
+
"model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 426 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 427 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 428 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 429 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 430 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 431 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 432 |
+
"model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 433 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 434 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 435 |
+
"model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 436 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 437 |
+
"model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 438 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 439 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 440 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 441 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 442 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 443 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 444 |
+
"model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 445 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 446 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 447 |
+
"model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 448 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 449 |
+
"model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 450 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 451 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 452 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 453 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 454 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 455 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 456 |
+
"model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 457 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 458 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 459 |
+
"model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 460 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 461 |
+
"model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 462 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 463 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 464 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 465 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 466 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 467 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 468 |
+
"model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 469 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 470 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 471 |
+
"model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 472 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 473 |
+
"model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 474 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 475 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 476 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 477 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 478 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 479 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 480 |
+
"model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 481 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 482 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 483 |
+
"model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 484 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 485 |
+
"model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
| 486 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 487 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin",
|
| 488 |
+
"score.bias": "pytorch_model-00003-of-00003.bin",
|
| 489 |
+
"score.weight": "pytorch_model-00003-of-00003.bin"
|
| 490 |
+
}
|
| 491 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "<|endoftext|>",
|
| 36 |
+
"errors": "replace",
|
| 37 |
+
"model_max_length": 32768,
|
| 38 |
+
"pad_token": "<|endoftext|>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
upos.py
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import TokenClassificationPipeline,Qwen2Model,Qwen2PreTrainedModel
|
| 2 |
+
from transformers.modeling_outputs import TokenClassifierOutput
|
| 3 |
+
|
| 4 |
+
class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
|
| 5 |
+
def __init__(self,**kwargs):
|
| 6 |
+
import numpy
|
| 7 |
+
super().__init__(**kwargs)
|
| 8 |
+
x=self.model.config.label2id
|
| 9 |
+
y=[k for k in x if not k.startswith("I-")]
|
| 10 |
+
self.transition=numpy.full((len(x),len(x)),numpy.nan)
|
| 11 |
+
for k,v in x.items():
|
| 12 |
+
for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
|
| 13 |
+
self.transition[v,x[j]]=0
|
| 14 |
+
def check_model_type(self,supported_models):
|
| 15 |
+
pass
|
| 16 |
+
def postprocess(self,model_outputs,**kwargs):
|
| 17 |
+
import numpy
|
| 18 |
+
if "logits" not in model_outputs:
|
| 19 |
+
return self.postprocess(model_outputs[0],**kwargs)
|
| 20 |
+
m=model_outputs["logits"][0].numpy()
|
| 21 |
+
e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
|
| 22 |
+
z=e/e.sum(axis=-1,keepdims=True)
|
| 23 |
+
for i in range(m.shape[0]-1,0,-1):
|
| 24 |
+
m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
|
| 25 |
+
k=[numpy.nanargmax(m[0])]
|
| 26 |
+
for i in range(1,m.shape[0]):
|
| 27 |
+
k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
|
| 28 |
+
w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
|
| 29 |
+
if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
|
| 30 |
+
for i,t in reversed(list(enumerate(w))):
|
| 31 |
+
p=t.pop("entity")
|
| 32 |
+
if p.startswith("I-"):
|
| 33 |
+
w[i-1]["score"]=min(w[i-1]["score"],t["score"])
|
| 34 |
+
w[i-1]["end"]=w.pop(i)["end"]
|
| 35 |
+
elif p.startswith("B-"):
|
| 36 |
+
t["entity_group"]=p[2:]
|
| 37 |
+
else:
|
| 38 |
+
t["entity_group"]=p
|
| 39 |
+
for t in w:
|
| 40 |
+
t["text"]=model_outputs["sentence"][t["start"]:t["end"]]
|
| 41 |
+
return w
|
| 42 |
+
|
| 43 |
+
class Qwen2ForTokenClassification(Qwen2PreTrainedModel):
|
| 44 |
+
def __init__(self,config):
|
| 45 |
+
from torch import nn
|
| 46 |
+
super().__init__(config)
|
| 47 |
+
self.num_labels=config.num_labels
|
| 48 |
+
self.model=Qwen2Model(config)
|
| 49 |
+
if getattr(config,"classifier_dropout",None) is not None:
|
| 50 |
+
classifier_dropout=config.classifier_dropout
|
| 51 |
+
elif getattr(config,"hidden_dropout",None) is not None:
|
| 52 |
+
classifier_dropout=config.hidden_dropout
|
| 53 |
+
else:
|
| 54 |
+
classifier_dropout=0.1
|
| 55 |
+
self.dropout=nn.Dropout(classifier_dropout)
|
| 56 |
+
self.score=nn.Linear(config.hidden_size,config.num_labels)
|
| 57 |
+
self.post_init()
|
| 58 |
+
def get_input_embeddings(self):
|
| 59 |
+
return self.model.embed_tokens
|
| 60 |
+
def set_input_embeddings(self,value):
|
| 61 |
+
self.model.embed_tokens=value
|
| 62 |
+
def forward(self,input_ids=None,past_key_values=None,attention_mask=None,position_ids=None,inputs_embeds=None,labels=None,use_cache=None,output_attentions=None,output_hidden_states=None,return_dict=None):
|
| 63 |
+
return_dict=return_dict if return_dict is not None else self.config.use_return_dict
|
| 64 |
+
outputs=self.model(input_ids,past_key_values=past_key_values,attention_mask=attention_mask,position_ids=position_ids,inputs_embeds=inputs_embeds,use_cache=use_cache,output_attentions=output_attentions,output_hidden_states=output_hidden_states,return_dict=return_dict)
|
| 65 |
+
sequence_output=outputs[0]
|
| 66 |
+
sequence_output=self.dropout(sequence_output)
|
| 67 |
+
logits=self.score(sequence_output)
|
| 68 |
+
loss=None
|
| 69 |
+
if labels is not None:
|
| 70 |
+
from torch import nn
|
| 71 |
+
loss_fct=nn.CrossEntropyLoss()
|
| 72 |
+
loss=loss_fct(logits.view(-1,self.num_labels),labels.view(-1))
|
| 73 |
+
if not return_dict:
|
| 74 |
+
output=(logits,)+outputs[2:]
|
| 75 |
+
return ((loss,)+output) if loss is not None else output
|
| 76 |
+
return TokenClassifierOutput(loss=loss,logits=logits,hidden_states=outputs.hidden_states,attentions=outputs.attentions)
|
| 77 |
+
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|