Add title and description NER checkpoint folders

README.md

@@ -0,0 +1,77 @@
+Here’s a clean `README.md` template for your Hugging Face repo with **both NER models** and usage instructions:
+
+# Job NER Pipeline Models
+
+This repository contains two pretrained NER models for job-related text processing:
+
+1. **Job Title NER** (`title_ner/`)  
+   Detects entities in job titles.
+
+2. **Job Description NER** (`desc_ner/`)  
+   Detects entities in full job descriptions.
+
+Both models include:
+- `model.safetensors` (weights)
+- `config.json`
+- `tokenizer.json`
+- `tokenizer_config.json`
+- `special_tokens_map.json`
+
+## Repository Structure
+
+README.md
+title_ner/
+model.safetensors
+config.json
+tokenizer.json
+tokenizer_config.json
+special_tokens_map.json
+desc_ner/
+model.safetensors
+config.json
+tokenizer.json
+tokenizer_config.json
+special_tokens_map.json
+
+## Usage
+
+Install required packages:
+```bash
+pip install transformers huggingface_hub
+````
+
+Load models in Python:
+
+```python
+from huggingface_hub import snapshot_download
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+# Download full repo
+repo_dir = snapshot_download("username/job-ner-pipeline")
+
+# Job Title NER
+title_path = f"{repo_dir}/title_ner"
+title_model = AutoModelForTokenClassification.from_pretrained(title_path)
+title_tokenizer = AutoTokenizer.from_pretrained(title_path)
+
+# Job Description NER
+desc_path = f"{repo_dir}/desc_ner"
+desc_model = AutoModelForTokenClassification.from_pretrained(desc_path)
+desc_tokenizer = AutoTokenizer.from_pretrained(desc_path)
+```
+
+You can now use these models in your pipeline for entity recognition on job titles and descriptions.
+
+---
+
+## Notes
+
+* Both models are required for the full pipeline.
+* Do **not modify the folder names**; the pipeline expects `title_ner` and `desc_ner`.
+* Large files (`.safetensors`) are tracked using Git LFS. Ensure you have it installed:
+
+```bash
+git lfs install
+```
+
+

jd-distilbert-job-ner/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "[BENEFITS]": 30522,
+  "[RESPONSIBILITIES]": 30523,
+  "[SKILLS]": 30524
+}

jd-distilbert-job-ner/config.json

@@ -0,0 +1,41 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-BENEFIT",
+    "2": "I-BENEFIT",
+    "3": "B-RESPONSIBILITY",
+    "4": "I-RESPONSIBILITY",
+    "5": "B-SKILL",
+    "6": "I-SKILL"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-BENEFIT": 1,
+    "B-RESPONSIBILITY": 3,
+    "B-SKILL": 5,
+    "I-BENEFIT": 2,
+    "I-RESPONSIBILITY": 4,
+    "I-SKILL": 6,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30525
+}

jd-distilbert-job-ner/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e7f2600abf1e6f7b38ba1cbd48cd0967df0055eeed43c239d0515f6b2a56da
+size 265494612

jd-distilbert-job-ner/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[BENEFITS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[RESPONSIBILITIES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[SKILLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

jd-distilbert-job-ner/tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "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
+    },
+    "30522": {
+      "content": "[BENEFITS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30523": {
+      "content": "[RESPONSIBILITIES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30524": {
+      "content": "[SKILLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[BENEFITS]",
+    "[RESPONSIBILITIES]",
+    "[SKILLS]"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

title-distilbert-job-ner/config.json

@@ -0,0 +1,65 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-LEVEL",
+    "2": "I-LEVEL",
+    "3": "B-ROLE",
+    "4": "I-ROLE",
+    "5": "B-FUNCTION",
+    "6": "I-FUNCTION",
+    "7": "B-DOMAIN",
+    "8": "I-DOMAIN",
+    "9": "B-TECH_STACK",
+    "10": "I-TECH_STACK",
+    "11": "B-REGION",
+    "12": "I-REGION",
+    "13": "B-WORK_SETTING",
+    "14": "I-WORK_SETTING",
+    "15": "B-EMPLOYMENT_TYPE",
+    "16": "I-EMPLOYMENT_TYPE",
+    "17": "B-LANGUAGE",
+    "18": "I-LANGUAGE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-DOMAIN": 7,
+    "B-EMPLOYMENT_TYPE": 15,
+    "B-FUNCTION": 5,
+    "B-LANGUAGE": 17,
+    "B-LEVEL": 1,
+    "B-REGION": 11,
+    "B-ROLE": 3,
+    "B-TECH_STACK": 9,
+    "B-WORK_SETTING": 13,
+    "I-DOMAIN": 8,
+    "I-EMPLOYMENT_TYPE": 16,
+    "I-FUNCTION": 6,
+    "I-LANGUAGE": 18,
+    "I-LEVEL": 2,
+    "I-REGION": 12,
+    "I-ROLE": 4,
+    "I-TECH_STACK": 10,
+    "I-WORK_SETTING": 14,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.56.2",
+  "vocab_size": 30522
+}

title-distilbert-job-ner/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dbd698faea6d5bc75295232ade8fb061cbedafd79f650b9dbdd75548f3decc
+size 265522308

title-distilbert-job-ner/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

title-distilbert-job-ner/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}