Upload v1 ship model (format v1)

README.md

@@ -0,0 +1,66 @@
+---
+language: en
+tags:
+  - sentence-transformers
+  - web-agent
+  - bi-encoder
+  - element-selection
+  - mind2web
+license: apache-2.0
+datasets:
+  - osunlp/Mind2Web
+pipeline_tag: feature-extraction
+---
+
+# Web Agent Bi-Encoder (v1)
+
+A fine-tuned bi-encoder for web element selection, trained on the Mind2Web dataset.
+
+## What this model does
+
+Given a natural-language task description (e.g., "click the search button") and a set
+of serialized web page elements, this model identifies the correct element to interact with.
+
+## Training
+
+- **Base model**: BAAI/bge-small-en-v1.5
+- **Training data**: Mind2Web (~5825 examples)
+- **Loss**: MultipleNegativesRankingLoss
+- **Format version**: v1
+
+## Evaluation
+
+- **Top-1 accuracy**: 80.4%
+- **Δ vs zero-shot baseline**: +13.8 points
+- **Baseline**: BAAI/bge-small-en-v1.5
+
+## Serialization format
+
+This model expects inputs serialized in the web-agent v1 format. See the
+repository's `docs/spec/03-node-serialization.md` for the full specification.
+Models trained on a different format version are incompatible.
+
+## Limitations
+
+- Trained primarily on English-language web tasks
+- US-centric site distribution in Mind2Web
+- Dataset collected circa 2023; some site layouts may have changed
+- Best for common web interaction patterns (forms, search, navigation)
+
+## Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("doeve/web-agent-bge-small-v1", revision="v1.0.0")
+query_emb = model.encode(["search for flights"])
+candidate_embs = model.encode(["textbox \"Search\" | — | in form:\"\", ..."])
+```
+
+Or via Transformers.js in the browser:
+
+```javascript
+import { pipeline } from "@huggingface/transformers";
+const extractor = await pipeline("feature-extraction", "doeve/web-agent-bge-small-v1",
+  { revision: "v1.0.0", dtype: "q8" });
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fdd4585308c83281af31267a722e26748fc432fee9e9d40181d17f2c00a3e2
+size 34000281

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

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": true,
+    "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": "QInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}

sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_meta.json

@@ -0,0 +1,30 @@
+{
+  "base_model": "BAAI/bge-small-en-v1.5",
+  "batch_size": 32,
+  "epochs": 4,
+  "learning_rate": 2e-05,
+  "warmup_ratio": 0.1,
+  "max_seq_length": 256,
+  "loss_scale": 20.0,
+  "train_rows": 5825,
+  "train_examples": 34950,
+  "val_rows": 638,
+  "device": "cpu",
+  "val_metrics": {
+    "val_cosine_accuracy@1": 0.588,
+    "val_cosine_accuracy@3": 0.794,
+    "val_cosine_accuracy@5": 0.872,
+    "val_cosine_accuracy@10": 0.94,
+    "val_cosine_precision@1": 0.588,
+    "val_cosine_precision@3": 0.2646666666666666,
+    "val_cosine_precision@5": 0.1744,
+    "val_cosine_precision@10": 0.094,
+    "val_cosine_recall@1": 0.588,
+    "val_cosine_recall@3": 0.794,
+    "val_cosine_recall@5": 0.872,
+    "val_cosine_recall@10": 0.94,
+    "val_cosine_ndcg@10": 0.76452976031552,
+    "val_cosine_mrr@10": 0.7081841269841267,
+    "val_cosine_map@100": 0.7095647550152437
+  }
+}

web_agent_stamp.json

@@ -0,0 +1,16 @@
+{
+  "format_version": "v1",
+  "training_phase": 1,
+  "trained_on": "2026-04-29",
+  "base_model": "BAAI/bge-small-en-v1.5",
+  "training_data_size": 5825,
+  "training_data_source": "mind2web",
+  "metrics_summary": {
+    "top1_acc": 0.8042,
+    "vs_baseline_delta": 0.1379,
+    "baseline": "BAAI/bge-small-en-v1.5"
+  },
+  "tokenizer_max_length": 256,
+  "embedding_dim": 384,
+  "use_mean_pooling": true
+}