Upload FactGuard

README.md

@@ -0,0 +1,67 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- text-classification
+- hallucination-detection
+- grounding
+- factual-consistency
+- nli
+- rag
+datasets:
+- stanfordnlp/snli
+- nyu-mll/multi_nli
+- anli
+pipeline_tag: text-classification
+---
+
+# 🛡️ FactGuard
+
+Lightweight hallucination and grounding detection model. Checks whether a claim is supported by the given context.
+
+Built on [ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) (149M params), fine-tuned on 1M+ NLI pairs from SNLI, MultiNLI, and ANLI.
+
+**Classes:** Supported, Not Supported
+
+## 🚀 Usage
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="ENTUM-AI/FactGuard")
+
+result = classifier({
+    "text": "Apple reported revenue of $94.8 billion in Q1 2024.",
+    "text_pair": "Apple's Q1 2024 revenue was $94.8 billion."
+})
+# [{'label': 'Supported', 'score': 0.99}]
+
+result = classifier({
+    "text": "Apple reported revenue of $94.8 billion in Q1 2024.",
+    "text_pair": "Apple's revenue exceeded $100 billion."
+})
+# [{'label': 'Not Supported', 'score': 0.97}]
+```
+
+## 📊 Training Data
+
+| Dataset | Samples |
+|---------|---------|
+| [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) | ~550K |
+| [nyu-mll/multi_nli](https://huggingface.co/datasets/nyu-mll/multi_nli) | ~393K |
+| [anli](https://huggingface.co/datasets/anli) | ~163K |
+
+1M+ NLI pairs mapped to binary grounding labels.
+
+## 🔍 Use Cases
+
+- **RAG pipelines** — verify LLM responses against source documents
+- **Fact-checking** — detect unsupported claims in generated text
+- **Content moderation** — flag hallucinated content before publishing
+
+## ⚠️ Limitations
+
+- English only
+- Designed for single claim verification against a given context

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Not Supported",
+    "1": "Supported"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "Not Supported": 0,
+    "Supported": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "use_cache": false,
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca692bc1e264ae0d6febb14e04ea93452616592a2c1eb461c0e67fbdc75d4ee3
+size 598439784

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}