int8 encoder (feature-extraction) for triple autofill

README.md

@@ -0,0 +1,3 @@
+# form-autofill-embed
+
+Quantized (int8) shared encoder for the Firefox triple-encoder autofill field classifier. Vocab-pruned multilingual MiniLM (BERT arch, 4 layers, hidden 384, vocab ~12.5k). Use as a **feature-extraction** model and mean-pool the `last_hidden_state` to a 384-d per-field embedding. Weights: `onnx/model_quantized.onnx` (int8). Pairs with `rolf-mozilla/form-autofill-head`.

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 12455
+}

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c8c8560a5889ee9b85fa549f92ccc0d696656cf8837a29dfc9f7e4c6934be0
+size 12473174

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}