Upload folder using huggingface_hub

app.py

@@ -1,36 +1,33 @@
+
 import gradio as gr
 from transformers import pipeline
 
 # The pipeline will automatically load the model and tokenizer
-# from the current directory where you've put the files.
+# from the directory where the app is running.
 try:
-    classifier = pipeline("text-classification", model="Unknownhackerr/hate_check_india", tokenizer="./")
+    classifier = pipeline("text-classification", model="./", tokenizer="./")
 
     def classify_text(text):
-        """
-        Classifies a single piece of text and returns a human-readable prediction.
-        """
         if not text:
             return "Please enter some text to classify."
             
         result = classifier(text)[0]
+        # Map the default labels to more descriptive ones
         label = "Hate Speech" if result['label'] == 'LABEL_1' else "Not Hate Speech"
         score = result['score']
         return f"Prediction: {label}\nConfidence: {score:.4f}"
 
-    # Create the Gradio interface
     iface = gr.Interface(
         fn=classify_text,
         inputs=gr.Textbox(lines=5, placeholder="Enter a comment in English or Hindi..."),
         outputs=gr.Textbox(label="Result"),
         title="Multilingual Hate Speech Classifier",
-        description="A model to classify comments in Hindi and English."
+        description="A model to classify comments as hate speech or not."
     )
     
     iface.launch()
     
 except Exception as e:
-    # A simple error message box for the user
     gr.Interface(
         lambda x: f"An error occurred: {e}",
         inputs="text",
@@ -38,4 +35,3 @@ except Exception as e:
         title="Error Loading Model",
         description="There was an issue loading the model. Please check your files and dependencies."
     ).launch()
-    

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b645672416dd4ed934c4c67dc0b4060132ef8c269bc70b173270a7bdab3d2e7
+size 498612824

requirements.txt

@@ -1,2 +1,4 @@
+
+transformers
+torch
 gradio
-transformers

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}