Upload fine-tuned DeBERTa-v3-large hallucination model

README.md

@@ -0,0 +1,41 @@
+---
+license: agpl-3.0
+language: en
+tags:
+  - hallucination-detection
+  - nli
+  - deberta-v3
+  - director-ai
+datasets:
+  - pminervini/HaluEval
+  - pietrolesci/nli_fever
+  - tals/vitaminc
+  - anli
+base_model: MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli
+pipeline_tag: text-classification
+---
+
+# DeBERTa-v3-large -- Hallucination Detection
+
+Fine-tuned for hallucination detection as part of
+[Director-AI](https://github.com/anulum/director-ai).
+
+## Training
+
+- **Base**: MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli
+- **Data**: ~100K examples from HaluEval, FEVER, VitaminC, ANLI R3
+- **Epochs**: 3, lr 2e-5, batch 32 (effective), class-weighted CE loss
+- **Labels**: 0 = entailment, 1 = neutral, 2 = contradiction
+
+## Usage
+
+```python
+from director_ai.core import NLIScorer
+
+scorer = NLIScorer(model_name="anulum/deberta-v3-large-hallucination")
+score = scorer.score("The capital of France is Paris.", "Paris is in Germany.")
+```
+
+## License
+
+AGPL-3.0 | Commercial licensing: [anulum.li](https://www.anulum.li)

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": "4.51.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

final_metrics.json

@@ -0,0 +1,12 @@
+{
+  "eval_loss": 0.3152,
+  "eval_accuracy": 0.9106,
+  "eval_f1": 0.8897,
+  "eval_f1_entailment": 0.948,
+  "eval_f1_neutral": 0.8246,
+  "eval_f1_contradiction": 0.8965,
+  "eval_runtime": 732.7963,
+  "eval_samples_per_second": 100.201,
+  "eval_steps_per_second": 3.132,
+  "epoch": 0.1937
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c6cf7d9945143581b8c517d1d44f5717d6fed156b354fcd995b6eb89570163
+size 1740308548

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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": false,
+      "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a511b7432da657c4e6744c1684e63afca070c0b26d8251a06b7afe188dcc464
+size 5777