Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,20 @@
+---
+license: mit
+library_name: setfit
+pipeline_tag: text-classification
+tags: [setfit, sentence-transformers, email-classification]
+---
+
+# JobTracker hybrid classifier — SetFit layer
+
+The few-shot ML layer of JobTracker's 3-layer email classifier
+(rules -> e5-small-v2 similarity -> SetFit). Classifies job-pipeline
+emails into stages: applied, assessment, follow_up, interview, offer,
+other, pending_application, rejection.
+
+- CI-gated at a 0.95 macro-F1 floor; **0.979 measured** on the committed
+  v3 evaluation set, alongside a 182-test suite.
+- An int8-ONNX export of this model powers the in-browser demo (zero
+  servers), verified output-identical to this pipeline.
+
+Part of the JobTracker project by Ayush Yadav.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.2.2",
+    "transformers": "4.57.6",
+    "pytorch": "2.10.0"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

config_setfit.json

@@ -0,0 +1,13 @@
+{
+  "normalize_embeddings": false,
+  "labels": [
+    "applied",
+    "assessment",
+    "follow_up",
+    "interview",
+    "offer",
+    "other",
+    "pending_application",
+    "rejection"
+  ]
+}

label_mapping.txt

@@ -0,0 +1,8 @@
+0:applied
+1:assessment
+2:follow_up
+3:interview
+4:offer
+5:other
+6:pending_application
+7:rejection

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c55166909f82e21aba0f629eda47d6d05aa2943b1e2f4169e6075e0f8db6b2e
+size 90864192

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6568fb5e41f415de27dc11e2dea049274573d893823946991256c4643956e24
+size 25543

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

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 +1,58 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_metadata.json

@@ -0,0 +1,91 @@
+{
+  "base_model": "sentence-transformers/paraphrase-MiniLM-L6-v2",
+  "eval_split_size": 20,
+  "id_to_label": {
+    "0": "applied",
+    "1": "assessment",
+    "2": "follow_up",
+    "3": "interview",
+    "4": "offer",
+    "5": "other",
+    "6": "pending_application",
+    "7": "rejection"
+  },
+  "label_counts": {
+    "applied": 24,
+    "assessment": 24,
+    "follow_up": 24,
+    "interview": 24,
+    "offer": 24,
+    "other": 24,
+    "pending_application": 24,
+    "rejection": 24
+  },
+  "label_source_counts": {
+    "applied": {
+      "external_dataset": 8,
+      "mock_seed_v3": 4,
+      "user_correction": 12
+    },
+    "assessment": {
+      "external_dataset": 8,
+      "mock_seed_v2": 7,
+      "mock_seed_v3": 8,
+      "user_correction": 1
+    },
+    "follow_up": {
+      "external_dataset": 8,
+      "mock_seed_v2": 8,
+      "mock_seed_v3": 8
+    },
+    "interview": {
+      "external_dataset": 8,
+      "mock_seed_v2": 8,
+      "mock_seed_v3": 8
+    },
+    "offer": {
+      "external_dataset": 2,
+      "mock_seed": 2,
+      "mock_seed_v2": 10,
+      "mock_seed_v3": 10
+    },
+    "other": {
+      "external_dataset": 8,
+      "mock_seed_v3": 5,
+      "user_correction": 11
+    },
+    "pending_application": {
+      "mock_seed": 2,
+      "mock_seed_v2": 9,
+      "mock_seed_v3": 10,
+      "user_correction": 3
+    },
+    "rejection": {
+      "external_dataset": 8,
+      "mock_seed_v3": 4,
+      "user_correction": 12
+    }
+  },
+  "label_to_id": {
+    "applied": 0,
+    "assessment": 1,
+    "follow_up": 2,
+    "interview": 3,
+    "offer": 4,
+    "other": 5,
+    "pending_application": 6,
+    "rejection": 7
+  },
+  "max_saved_models": 3,
+  "schema_version": 1,
+  "source_counts": {
+    "external_dataset": 50,
+    "mock_seed": 4,
+    "mock_seed_v2": 42,
+    "mock_seed_v3": 57,
+    "user_correction": 39
+  },
+  "total_examples": 192,
+  "train_split_size": 172,
+  "trained_at": "2026-03-06T22:54:04.334060"
+}