Upload 15 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model-last/tok2vec/model filter=lfs diff=lfs merge=lfs -text
+model-last/vocab/key2row filter=lfs diff=lfs merge=lfs -text
+model-last/vocab/strings.json filter=lfs diff=lfs merge=lfs -text
+model-last/vocab/vectors filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,15 @@
+import spacy
+import gradio as gr
+
+nlp = spacy.load(r"./model-last")
+
+def ner(sentence):
+    doc = nlp(sentence)
+    ents = [(e.text, e.label_) for e in doc.ents]
+    return ents
+desc = "(GPE01)->臺北市、新北市、桃園市、臺中市、臺南市、高雄市。(GPE02)->新竹縣、苗栗縣、彰化縣、南投縣、雲林縣、嘉義縣、屏東縣、宜蘭縣、花蓮縣、臺東縣、澎湖縣、金門縣、連江縣。(GPE03)->基隆市、新竹市、嘉義市。"
+demo = gr.Interface(fn=ner, inputs="text",description=desc, outputs = "text")
+demo.launch()
+
+if __name__ == "__main__":
+    demo.launch()

model-last/config.cfg

@@ -0,0 +1,150 @@
+[paths]
+train = "./train.spacy"
+dev = "./train.spacy"
+vectors = "zh_core_web_lg"
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "zh"
+pipeline = ["tok2vec","ner"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[nlp.tokenizer]
+@tokenizers = "spacy.zh.ChineseTokenizer"
+segmenter = "char"
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = true
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 256
+depth = 8
+window_size = 1
+maxout_pieces = 3
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]
+pkuseg_model = null
+pkuseg_user_dict = "default"

model-last/meta.json

@@ -0,0 +1,64 @@
+{
+  "lang":"zh",
+  "name":"pipeline",
+  "version":"0.0.0",
+  "spacy_version":">=3.7.2,<3.8.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"a89eae928",
+  "vectors":{
+    "width":300,
+    "vectors":500000,
+    "keys":500000,
+    "name":"zh_vectors",
+    "mode":"default"
+  },
+  "labels":{
+    "tok2vec":[
+
+    ],
+    "ner":[
+      "GPE01",
+      "GPE02",
+      "GPE03"
+    ]
+  },
+  "pipeline":[
+    "tok2vec",
+    "ner"
+  ],
+  "components":[
+    "tok2vec",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "ents_f":1.0,
+    "ents_p":1.0,
+    "ents_r":1.0,
+    "ents_per_type":{
+      "GPE01":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "GPE02":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "GPE03":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      }
+    },
+    "tok2vec_loss":0.0000000001,
+    "ner_loss":0.0000000016
+  }
+}

model-last/ner/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

model-last/ner/moves

@@ -0,0 +1 @@
+��movesٰ{"0":{},"1":{"GPE02":39,"GPE01":18,"GPE03":9},"2":{"GPE02":39,"GPE01":18,"GPE03":9},"3":{"GPE02":39,"GPE01":18,"GPE03":9},"4":{"GPE02":39,"GPE01":18,"GPE03":9,"":1},"5":{"":1}}�cfg��neg_key�

model-last/tok2vec/cfg

@@ -0,0 +1,3 @@
+{
+
+}

model-last/tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8098b73e264c5bd0436ce0ba7dfebe6fa480c8816a13e6e93390984f0184935d
+size 34434008

model-last/tokenizer/cfg

@@ -0,0 +1,3 @@
+{
+  "segmenter":"char"
+}

model-last/vocab/key2row

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5743a5bd0280a49eaf03e67ecb1a1fa93f04080c8d5802c4562e5004f46c48
+size 6868315

model-last/vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

model-last/vocab/strings.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4701b348a784457e18cdd9c993c5d8c5ea0875785776356c77c61d2d0eaf67d2
+size 10515213

model-last/vocab/vectors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761b22330b44dfde9c65f6646d02c785e3935b34410802e4fc9297ca3b5ba3f6
+size 600000128

model-last/vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}

requirements.txt

@@ -0,0 +1 @@
+spacy