Upload folder using huggingface_hub

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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": "4.44.0",
+  "vocab_size": 30522
+}

inference.py

@@ -0,0 +1,25 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+def model_fn(model_dir):
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+    model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+    return model, tokenizer
+
+def predict_fn(data, model_and_tokenizer):
+    model, tokenizer = model_and_tokenizer
+    
+    # Assuming 'inputs' is the key in the input data
+    inputs = data.pop("inputs", data)
+    
+    # Tokenize the input
+    tokenized = tokenizer(inputs, return_tensors="pt", padding=True, truncation=True)
+    
+    # Make the prediction
+    with torch.no_grad():
+        output = model(**tokenized)
+    
+    # Get the predicted class (assuming it's a classification task)
+    predicted_class = torch.argmax(output.logits, dim=1).item()
+    
+    return {"predicted_class": predicted_class}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7b6229d87c79c3dcdc64c5f8ac75e1bd9d4cde915bfe54eb3a1517904905d1
+size 267844872

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79e3502b1d97164965cbfea5b1f9e32d9d08dd3dca7f2f13918aecc0ef1c14f
+size 535751866

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7b6229d87c79c3dcdc64c5f8ac75e1bd9d4cde915bfe54eb3a1517904905d1
+size 267844872

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fc017371029f0bef030c8c9dd52c8c484c2d3cf83565614b75fe5386bee2bc
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34434eb7a6f998337174c8743ff5c28ee6ee743c7ffed8be104b01af48e27d27
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6faebe82668ee2b7d63b4d99a51dd4f8b991b2dfeb4ea40b92d0bd578d0a78
+size 5112