OpenDecision-Large-Packed 0.1.0

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,120 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: opendecision
+pipeline_tag: zero-shot-classification
+base_model: microsoft/deberta-v3-large
+tags:
+- decision
+- text-classification
+- intent-classification
+- routing
+- zero-shot-classification
+- multi-label
+- deberta-v3
+datasets:
+- fastino/fast-decisions
+- stanfordnlp/snli
+- fancyzhx/dbpedia_14
+- mteb/banking77
+---
+
+# OpenDecision-Large-Packed
+
+📄 Technical report: [*OpenDecision: Fast Schema-Conditioned Decisions with Packed Candidate Encoding*](https://github.com/tokz-labs/OpenDecision/releases/latest/download/OpenDecision.pdf) (PDF; arXiv version coming soon) · [Code](https://github.com/tokz-labs/OpenDecision)
+
+OpenDecision-Large-Packed is the low-cost variant of
+[OpenDecision-Large](https://huggingface.co/Tokz-labs/OpenDecision-Large): the same
+433.9M-parameter DeBERTa-v3-large decision model, using a **packed candidate
+encoder** that scores up to 16 options in one forward pass. The input text is encoded once
+per pack; attention masks and per-sequence relative positions give every option the same
+view it would have alone, so answers do not depend on option order.
+
+## Usage
+
+```bash
+pip install "opendecision @ git+https://github.com/tokz-labs/OpenDecision"
+```
+
+```python
+from opendecision import OpenDecision, Choice, Bool, MultiLabel
+
+model = OpenDecision.from_pretrained("Tokz-labs/OpenDecision-Large-Packed")
+out = model.decide(
+    "I was charged twice for my May invoice and the app keeps logging me out.",
+    {
+        "queue": Choice(["billing", "technical", "account", "sales"]),
+        "tags": MultiLabel(["double_charge", "login_issue", "refund_request", "outage"]),
+        "urgent": Bool(),
+    },
+)
+print(out["queue"].best, out["tags"].selected, out["urgent"].policy)
+```
+
+## Efficiency
+
+GPU-seconds per 1,000 decisions on the complete classification-suite test sets, one NVIDIA L4:
+
+| Model | All five tasks | Without CLINC150 (151 options) | $ / 1k decisions (L4 list price) |
+|---|---|---|---|
+| **OpenDecision-Large-Packed** | 69.1 | **34.8** | 0.0153 |
+| OpenDecision-Large (cross-encoder) | 77.4 | 58.9 | 0.0172 |
+| Laya | 43.5 | 41.2 | 0.0097 |
+| JevK5 v0.3 (4B) | 267.4 | 119.9 | 0.0594 |
+| SemIf (4B) | 275.0 | 130.4 | 0.0611 |
+
+Packing pays off for questions with up to ~16 options; with many more (CLINC150's 151 intents) the
+cross-encoder is faster. Batch-size-1 latency (L4, bf16, p50): 66 ms for a short
+text with 10 options; 69 ms for a 512-token text with 10 options
+(cross-encoder: 248 ms).
+
+## Benchmarks
+
+Classification suite, complete test sets, macro-F1 (open models, identical inputs; GLiNER2.5 with its
+best interface per dataset):
+
+| Model | AG News | CLINC150 | IMDb | Rotten Tomatoes | XNLI | Average |
+|---|---|---|---|---|---|---|
+| OpenDecision-Large | 87.37 | 76.38 | 94.84 | 92.03 | 88.93* | 87.91 |
+| **OpenDecision-Large-Packed** | 86.70 | 75.95 | 94.59 | 89.96 | 88.97* | 87.23 |
+| SemIf (Qwen3.5-4B, 4B) | 87.28 | 78.22 | 95.27 | 88.46 | 82.36 | 86.32 |
+| JevK5 v0.3 (4B) | 85.45 | 79.86 | 95.06 | 87.60 | 83.40 | 86.27 |
+| Laya (421M) | 92.42 | 47.57 | 92.16 | 87.99 | 87.22 | 81.47 |
+| GLiFormer large-v1 (576M) | 82.88 | 59.49 | 94.19 | 84.06 | 82.03 | 80.53 |
+| GLiNER2.5-Decide (340M) | 71.37 | 66.19 | 90.02 | 85.83 | 47.65 | 72.21 |
+
+\* NLI data is in the training data: XNLI is not zero-shot.
+
+On label sets that no training data targeted, averaged over TREC question types, Emotion and
+Subjectivity, it scores 55.64 macro-F1 (OpenDecision-Large 57.00,
+Laya 62.11, SemIf 64.29, JevK5 72.07); its final training
+stage, which adds 15,942 LLM-invented classification tasks with these task families excluded,
+raised this from 45.70. GoEmotions multi-label exact match is low
+(13.30; the model selects too many labels). For a new kind of decision, fine-tune on a
+few hundred labeled examples (`python -m opendecision.cli.train`).
+
+## Training data
+
+Two stages from DeBERTa-v3-large (the packed stage starts from the clean cross-encoder) on LLM-generated decisions and LLM-invented classification tasks (OpenAI models), the Fast Decisions
+public development split, MultiNLI, WANLI and samples of DBpedia-14, BANKING77, SNLI, WikiText-103 and
+20 Newsgroups (Mitchell 1997, CC BY 4.0). Every source allows commercial use under its license; sources
+and licenses are listed in the technical report.
+
+## Scope and limitations
+
+English only; inputs up to 512 tokens; options truncated to 48 tokens. Not a chat or
+reasoning model. The benchmarks above were also used to select training mixtures. Most
+training text was generated or labeled by OpenAI models.
+
+## Citation
+
+```bibtex
+@misc{alwarawreh2026opendecision,
+  title  = {OpenDecision: Fast Schema-Conditioned Decisions with Packed Candidate Encoding},
+  author = {Alwarawreh, Abdallah},
+  year   = {2026},
+  note   = {Tokz Labs technical report},
+  url    = {https://github.com/tokz-labs/OpenDecision/releases/latest/download/OpenDecision.pdf}
+}
+```

backbone_config.json

@@ -0,0 +1,31 @@
+{
+  "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,
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 0,
+  "vocab_size": 128003
+}

config.json

@@ -0,0 +1,12 @@
+{
+  "architecture": "packed",
+  "backbone": "microsoft/deberta-v3-large",
+  "max_state_tokens": 512,
+  "max_candidate_tokens": 48,
+  "max_header_tokens": 20,
+  "cross_candidate_tokens": 32,
+  "row_chunk_size": 128,
+  "pack_size": 16,
+  "pack_candidate_tokens": 3072,
+  "pack_cell_budget": 6000000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7612f6e57031dd0a25fb3f18c95f91a6a1638624d84e7e900cf8025bfa514a1f
+size 1735709104

tokenizer/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "[CAND]": 128002,
+  "[DEC]": 128001,
+  "[MASK]": 128000
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[DEC]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[CAND]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

tokenizer/spm.model

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

tokenizer/tokenizer_config.json

@@ -0,0 +1,79 @@
+{
+  "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
+    },
+    "128001": {
+      "content": "[DEC]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "[CAND]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[DEC]",
+    "[CAND]"
+  ],
+  "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"
+}