add model shards to reduce memory consumption

.gitattributes

@@ -1 +1,2 @@
-static/*.csv filter=lfs diff=lfs merge=lfs -text
+static/*.csv filter=lfs diff=lfs merge=lfs -text
+static/model_shards/*.bin filter=lfs diff=lfs merge=lfs -text

main.py

@@ -25,7 +25,7 @@ templates = Jinja2Templates(directory="templates/")
 onet = pd.read_csv('static/ONET_JobTitles.csv')
 simdat = pd.read_csv('static/cohere_embeddings.csv')
 
-classifier = pipeline('text-classification', model='celise88/distilbert-base-uncased-finetuned-binary-classifier', tokenizer='celise88/distilbert-base-uncased-finetuned-binary-classifier')
+classifier = pipeline('text-classification', model = 'static/model_shards', tokenizer = 'static/tokenizer_shards')
 
 ### job information center ###
 # get
@@ -87,7 +87,6 @@ def get_resume(request: Request, resume: UploadFile = File(...)):
     with open(path, 'wb') as buffer:
         buffer.write(resume.file.read())
     file = Document(path)
-    print(file)
     text = []
     for para in file.paragraphs:
         text.append(para.text)

static/model_shards/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "celise88/distilbert-base-uncased-finetuned-binary-classifier",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "vocab_size": 30522
+}

static/model_shards/pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b71425a895e228378ca2e132485db2027a2d04fa588241bbe3c91d7557167be
+size 537

static/model_shards/pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6912a218252c3bd43d77edb6a94f9baea358e0ef3b0cbb1d7c565dff7317f67c
+size 93764522

static/model_shards/pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d000e5c4c8e8d61e178943368d71e1a9d2fc6c3ea9d9f58ade1668599ace06ed
+size 48846141

static/model_shards/pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3e308faaa42d27babfd6e8b29d65deeb66b109d0477a9e0c9f76a70af3ce3f
+size 47263787

static/model_shards/pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1951867aacee99f76ec6374166ff03869c8d5cca4004cfe496cd36e948b8c745
+size 49618047

static/model_shards/pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae443170da3a02b133bfd6f8bc2c8b2c205b1e89e7c38950886eeb920cb9f406
+size 28363923

static/model_shards/pytorch_model.bin.index.json

@@ -0,0 +1,111 @@
+{
+  "metadata": {
+    "total_size": 267820040
+  },
+  "weight_map": {
+    "classifier.bias": "pytorch_model-00006-of-00006.bin",
+    "classifier.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.embeddings.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.embeddings.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.embeddings.position_embeddings.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.embeddings.word_embeddings.weight": "pytorch_model-00002-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.k_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.k_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.out_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.out_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.q_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.q_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.v_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.attention.v_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.ffn.lin1.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.ffn.lin1.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.ffn.lin2.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.ffn.lin2.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.output_layer_norm.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.output_layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.sa_layer_norm.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.0.sa_layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.k_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.k_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.out_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.out_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.q_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.q_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.v_lin.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.attention.v_lin.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.ffn.lin1.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.ffn.lin1.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.ffn.lin2.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.1.ffn.lin2.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.1.output_layer_norm.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.1.output_layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.1.sa_layer_norm.bias": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.1.sa_layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.k_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.k_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.out_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.out_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.q_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.q_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.v_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.attention.v_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.ffn.lin1.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.ffn.lin1.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.ffn.lin2.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.ffn.lin2.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.output_layer_norm.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.output_layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.sa_layer_norm.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.2.sa_layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.k_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.k_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.out_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.out_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.q_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.q_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.v_lin.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.attention.v_lin.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.ffn.lin1.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.3.ffn.lin1.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.3.ffn.lin2.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.3.ffn.lin2.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.3.output_layer_norm.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.3.output_layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.3.sa_layer_norm.bias": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.3.sa_layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.k_lin.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.k_lin.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.out_lin.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.out_lin.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.q_lin.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.q_lin.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.v_lin.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.attention.v_lin.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.ffn.lin1.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.ffn.lin1.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.ffn.lin2.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.ffn.lin2.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.output_layer_norm.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.output_layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.sa_layer_norm.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.4.sa_layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.k_lin.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.k_lin.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.out_lin.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.out_lin.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.q_lin.bias": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.q_lin.weight": "pytorch_model-00005-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.v_lin.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.attention.v_lin.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.ffn.lin1.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.ffn.lin1.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.ffn.lin2.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.ffn.lin2.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.output_layer_norm.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.output_layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.sa_layer_norm.bias": "pytorch_model-00006-of-00006.bin",
+    "distilbert.transformer.layer.5.sa_layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "pre_classifier.bias": "pytorch_model-00006-of-00006.bin",
+    "pre_classifier.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

static/tokenizer_shards/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

static/tokenizer_shards/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "celise88/distilbert-base-uncased-finetuned-binary-classifier",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}