Upload 9 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

app.py

@@ -0,0 +1,48 @@
+# streamlit_app.py
+
+import streamlit as st
+import torch
+import torch.nn.functional as F
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from pathlib import Path
+import pandas as pd
+
+# Local model path
+MODEL_DIR = Path(__file__).parent
+
+# Device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load model and tokenizer
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_DIR)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
+model.to(device)
+model.eval()
+
+# Inference function
+def classify(prompt: str):
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, padding=True, max_length=512).to(device)
+    with torch.no_grad():
+        logits = model(**inputs).logits
+        probs = F.softmax(logits, dim=-1).squeeze().cpu()
+        pred = torch.argmax(probs).item()
+        confidence = probs[pred].item()
+        return pred, confidence
+
+# Streamlit UI
+st.title("QDG Classifier by DEJAN")
+user_input = st.text_area("Enter one prompt per line:")
+
+if st.button("Classify"):
+    prompts = [line.strip() for line in user_input.strip().split("\n") if line.strip()]
+    if not prompts:
+        st.warning("Please enter at least one prompt.")
+    else:
+        records = []
+        with st.spinner("Classifying..."):
+            for p in prompts:
+                label, conf = classify(p)
+                records.append({"Prompt": p, "Grounding": label, "Confidence": round(conf, 4)})
+
+        df = pd.DataFrame(records)
+        st.dataframe(df, use_container_width=True)

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8bc4c9eae6669edd4396d28294abb009a589c66c3a67f996bf0532ab44c415
+size 1740304440

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0166985261736faf29e9df13d24bffbb8ef9f3cb1b9daa31a46f97a13244f483
+size 5304