lkjfs

.gitignore

@@ -15,3 +15,6 @@ eval-results-bk/
 logs/
 
 emissions.csv
+
+.venv/
+.idea/

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "/content/drive/My Drive/FrugalAI/bert_fine_tuned_model",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2a203e16bd5abb95a639911210e8b926445771d3bf5714215d9faa0d8b1527
+size 437977104

requirements.txt

@@ -7,4 +7,7 @@ pydantic>=1.10.0
 python-dotenv>=1.0.0
 gradio>=4.0.0
 requests>=2.31.0
-librosa==0.10.2.post1
+librosa==0.10.2.post1
+torch~=2.5.1
+numpy~=2.0.2
+transformers>=4.30.0

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tasks/text.py

@@ -2,14 +2,16 @@ from fastapi import APIRouter
 from datetime import datetime
 from datasets import load_dataset
 from sklearn.metrics import accuracy_score
-import random
+import torch
+from torch.utils.data import Dataset, DataLoader
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
 from .utils.evaluation import TextEvaluationRequest
 from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
 router = APIRouter()
 
-DESCRIPTION = "Random Baseline"
+DESCRIPTION = "BERT Fine tuned"
 ROUTE = "/text"
 
 @router.post(ROUTE, tags=["Text Task"], 
@@ -58,7 +60,51 @@ async def evaluate_text(request: TextEvaluationRequest):
     
     # Make random predictions (placeholder for actual model inference)
     true_labels = test_dataset["label"]
-    predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
+    texts=test_dataset["quote"]
+    labels=test_dataset["label"]
+
+    model_dir = "./"
+
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+    model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+
+    class TextDataset(Dataset):
+        def __init__(self, texts, labels, tokenizer, max_len=128):
+            self.texts = texts
+            self.labels = labels
+            self.tokenizer = tokenizer
+            self.max_len = max_len
+
+        def __len__(self):
+            return len(self.texts)
+
+        def __getitem__(self, idx):
+            text = self.texts[idx]
+            label = self.labels[idx]
+            encodings = self.tokenizer(
+                text,
+                max_length=self.max_len,
+                padding='max_length',
+                truncation=True,
+                return_tensors="pt"
+            )
+            return {
+                'input_ids': encodings['input_ids'].squeeze(0),
+                'attention_mask': encodings['attention_mask'].squeeze(0),
+                'labels': torch.tensor(label, dtype=torch.long)
+            }
+
+    test_dataset = TextDataset(texts, labels, tokenizer)
+    test_loader = DataLoader(test_dataset, batch_size=16)
+
+    model.eval()
+    predictions = []
+    with torch.no_grad():
+        for inputs, labels in test_loader:
+            inputs, labels = inputs.to('cpu'), labels.to('cpu')
+            outputs = model(inputs)
+            _, predicted = torch.max(outputs, 1)
+            predictions.extend(predicted.cpu().numpy())
 
     #--------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE STOPS HERE

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}