Publish inference-only contextual model v0.1.0

README.md

@@ -0,0 +1,49 @@
+---
+library_name: premove-itn
+tags:
+  - inverse-text-normalization
+  - voice-agents
+  - custom-code
+license: mit
+---
+
+# Premove ITN Contextual v0.1.0
+
+This is the first frozen, inference-only artifact for Premove ITN's
+structured-value contextual scorer. It contains the complete trained model
+parameters in `model.safetensors`, the exact DeBERTa configuration, and the
+tokenizer files used by the selected production checkpoint. Optimizer state,
+schedulers, counters, and training datasets are not included.
+
+The artifact is loaded through the `premove-itn` package. It is not a generic
+Transformers model; use the package loader so candidate generation and scoring
+stay aligned with the release implementation:
+
+```python
+from premove_itn.inference_artifact import load_inference_artifact
+
+artifact = load_inference_artifact(".")
+model = artifact.model
+tokenizer = artifact.tokenizer
+```
+
+The model uses `microsoft/deberta-v3-large` at the exact revision recorded in
+`provenance.json`. The base model is referenced rather than redistributed.
+Microsoft's model card lists the base model and tokenizer under the MIT
+license; retain that attribution when redistributing this artifact.
+
+This release is tagged `v0.1.0`. Do not move or overwrite that tag after
+publication. The artifact digest and source checkpoint lineage are recorded in
+`provenance.json`.
+
+## Scope
+
+The supported span kinds are the values listed in `config.json`. This artifact
+selects deterministic Rust candidates with a contextual scorer. It does not
+contain training data or the frozen VoiceAgent benchmark dataset.
+
+## Release identity
+
+- Artifact version: `v0.1.0`
+- Architecture: `premove-candidate-scorer-v1`
+- Package version: `0.1.0`

base_config.json

@@ -0,0 +1,34 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "eos_token_id": null,
+  "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": 0.0,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architecture_version": "premove-candidate-scorer-v1",
+  "artifact_schema_version": 1,
+  "base_config_file": "base_config.json",
+  "base_model": "microsoft/deberta-v3-large",
+  "base_model_revision": "64a8c8eab3e352a784c658aef62be1662607476f",
+  "dropout": 0.1,
+  "kind_embedding_size": 32,
+  "model_max_tokens": 512,
+  "scorer_hidden_size": 256,
+  "state_dict_file": "model.safetensors",
+  "supported_span_kinds": [
+    "DIGIT_SEQUENCE",
+    "CARDINAL",
+    "TIME",
+    "DATE",
+    "MONEY",
+    "DECIMAL",
+    "PHONE",
+    "ELECTRONIC",
+    "MEASUREMENT",
+    "ORDINAL",
+    "PUNCTUATION",
+    "WHITELIST",
+    "WORD"
+  ],
+  "tokenizer_dir": "tokenizer",
+  "tokenizer_revision": "64a8c8eab3e352a784c658aef62be1662607476f"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119c0f19767b61446e04da1f8f01a001edf97a47a66965e7146db2483b4937a1
+size 1742425916

provenance.json

@@ -0,0 +1,41 @@
+{
+  "architecture": "premove-candidate-scorer-v1",
+  "artifact_sha256": "119c0f19767b61446e04da1f8f01a001edf97a47a66965e7146db2483b4937a1",
+  "artifact_sha256_definition": "SHA-256 of model.safetensors",
+  "artifact_version": "v0.1.0",
+  "hub_repository": "premove-itn/premove-itn-contextual",
+  "hub_revision": "v0.1.0",
+  "base_model": "microsoft/deberta-v3-large",
+  "base_model_revision": "64a8c8eab3e352a784c658aef62be1662607476f",
+  "benchmark_checkpoint_sha256": "9021fa11a028faefb31ef67878170cbe29ed25e68a9a78999f37b120c2ad00d5",
+  "package_version": "0.1.0",
+  "production_manifest": "data/models/structured_value_selected_20k/manifest.json",
+  "redistribution": {
+    "base_model_license": "MIT (as listed by microsoft/deberta-v3-large)",
+    "base_model_weights_included": false,
+    "project_license": "MIT",
+    "tokenizer_files_included": true
+  },
+  "source_checkpoint": "data/models/structured_value_selected_20k/checkpoint.pt",
+  "source_checkpoint_sha256": "9021fa11a028faefb31ef67878170cbe29ed25e68a9a78999f37b120c2ad00d5",
+  "supported_span_kinds": [
+    "DIGIT_SEQUENCE",
+    "CARDINAL",
+    "TIME",
+    "DATE",
+    "MONEY",
+    "DECIMAL",
+    "PHONE",
+    "ELECTRONIC",
+    "MEASUREMENT",
+    "ORDINAL",
+    "PUNCTUATION",
+    "WHITELIST",
+    "WORD"
+  ],
+  "tokenizer_revision": "64a8c8eab3e352a784c658aef62be1662607476f",
+  "training_lineage": {
+    "combined_exposure": 418000,
+    "run_fingerprint": "96c110801753166276df98ca9d65406f161009b8e981c03ca8cca94a9fb489fe"
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}