Publish third-pass feed ranker

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+language:
+- multilingual
+tags:
+- cross-encoder
+- reranker
+- feed-ranking
+- onnx
+- int8
+pipeline_tag: text-classification
+base_model: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
+library_name: optimum
+---
+
+# Third-Pass Feed Ranker — ONNX + INT8
+
+ONNX and dynamically-quantized **INT8** builds of the [third-pass feed ranker](../) for fast
+**CPU** inference. Same model, two files:
+
+| file | precision | size | notes |
+|---|---|---|---|
+| `model.onnx` | fp32 | ~471 MB | scores are **identical** to the PyTorch model |
+| `model_quantized.onnx` | int8 (dynamic) | ~118 MB | **4× smaller**; scores within ~0.05 of fp32 (ranking order preserved) |
+
+## CPU throughput (job_title × post scoring)
+Measured on a desktop CPU (AVX2/AVX-VNNI, no AVX-512), 8 threads:
+
+| build | items/sec |
+|---|---|
+| onnx fp32 | ~910 |
+| **onnx int8** | **~1080 (~1.2×)** |
+
+On **server CPUs with AVX-512 VNNI** (e.g. Intel Xeon Scalable), the INT8 speedup is typically
+**2–4×** — this desktop under-shows it. Absolute rates depend on post length.
+
+## Usage
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer
+import torch
+
+name = "you/third-pass-feed-ranker-onnx"
+tok = AutoTokenizer.from_pretrained(name)
+model = ORTModelForSequenceClassification.from_pretrained(name, file_name="model_quantized.onnx")  # or model.onnx
+
+title, posts = "Registered Nurse", ["Updated sepsis screening pathway is now live.", "Q3 revenue beat expectations!"]
+enc = tok([title]*len(posts), posts, truncation=True, max_length=160, padding=True, return_tensors="pt")
+scores = model(**enc).logits.squeeze(-1).tolist()   # higher = more relevant
+```
+
+The promotion/gate logic (which item to move to slot 1, and when) is **not** in the model — see
+the base model card for the decision-logic snippet. This repo only provides the CPU-optimized
+scorer. Trained on **synthetic data**; validate on your own before production. See the base model
+card for full evaluation, limitations, and license/attribution.

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77beb06a32bc9e45f34efee574f43a0c4d2cb0fb678f8ba9ea549d78d8997d6
+size 470787224

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7742ff5d5a1755222b2d5deabd097ed7ead0a25e1800265751b2ef27508a828d
+size 118276448

ort_config.json

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QUInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed3aba76839292e668a3726cf01dfaf90cbc141502955998c4bc233aac28ce6
+size 17082832

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "max_length": 160,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}