Grandes cosas sucediendo

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import torch
+import json
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+MODEL_PATH = "./model"
+
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, use_fast=False)
+    model = AutoModelForSequenceClassification.from_pretrained(MODEL_PATH)
+    model.eval()
+
+    with open(f"{MODEL_PATH}/label_mapping.json") as f:
+        label_mapping = json.load(f)
+
+    return tokenizer, model, label_mapping
+
+tokenizer, model, label_mapping = load_model()
+
+def predict(text: str):
+    if not text.strip():
+        return {}
+
+    inputs = tokenizer(
+        text,
+        return_tensors="pt",
+        padding="max_length",
+        truncation=True,
+        max_length=128,
+    )
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    probs = torch.softmax(logits, dim=-1).squeeze()
+    scores = {label_mapping[str(i)]: float(probs[i]) for i in range(len(probs))}
+    return scores
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(
+        lines=5,
+        placeholder="Write something",
+        label="Example Tweet"
+    ),
+    outputs=gr.Label(
+        num_top_classes=len(label_mapping),
+        label="Predicted Label"
+    ),
+    title="Radical Speech Detector",
+    description="Enter a text and the model will classify it into one of the radical speech categories.\n\n\nBy Sofia Maldonado, Viviana Toledo & Oscar Rocha",
+)
+
+demo.launch()

model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

model/config.json

@@ -0,0 +1,47 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "tokenizer_class": "BertweetTokenizer",
+  "transformers_version": "5.8.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 64001
+}

model/label_mapping.json

@@ -0,0 +1 @@
+{"0": "Dangerous Speech", "1": "Enraged Speech", "2": "Extreme Speech", "3": "Hate Grammar", "4": "Hate Speech", "5": "Horror Grammar"}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1793b6c2a2081de4b4c59fba90509e99bc84efc8a70a22b328c65c4d05afa61
+size 539642472

model/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalization": false,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BertweetTokenizer",
+  "unk_token": "<unk>"
+}

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6878f3da261338741aea81d888c67104a7be7587802d32fe22ca71a57cdb933d
+size 5265

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+transformers
+torch
+sentencepiece