Update README.md

README.md

@@ -29,7 +29,7 @@ Not designed for parsing **candidate resumes**.
 ### Training Data
 
 * **Synthetic internship and job description dataset** generated with **mostly.ai**
-* \~X,000 labeled samples (replace with actual dataset size if you know it)
+* \~20,000 labeled samples (replace with actual dataset size if you know it)
 * Labels: `SKILL`, `DISCIPLINE`, `COURSE`, `ROLE`
 
 ---
@@ -40,27 +40,35 @@ Not designed for parsing **candidate resumes**.
 import torch
 from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
 
-# Load model
+# Load from Hugging Face Hub
 model_name = "gmay29/ner_model_final"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForTokenClassification.from_pretrained(model_name)
 
-device = 0 if torch.cuda.is_available() else -1
+device = 0 if torch.cuda.is_available() else -1  # pipeline expects 0 for GPU, -1 for CPU
 
-# Create NER pipeline
-ner_pipeline = pipeline(
-    "ner",
-    model=model,
-    tokenizer=tokenizer,
-    device=device,
-    aggregation_strategy="simple"
-)
+# Create NER pipeline (handles context automatically)
+ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, device=device, aggregation_strategy="simple")
 
-# Example internship/job description
+# Example job description text
 text = """
+Details
 Responsibilities of the Intern:
-Design, develop, and implement AI agents for various applications.
-Strong programming skills in Python and experience with TensorFlow or PyTorch.
+
+Accurately enter and update data into the company's databases and systems.
+Maintain and organize digital and physical records.
+Assist in generating and compiling reports using data from various sources.
+Perform data quality checks to ensure accuracy and completeness.
+Support the team with other administrative tasks as needed.
+Requirements:
+
+Strong data entry skills with high accuracy and attention to detail.
+Proficiency in Microsoft Excel and other data management tools.
+Basic understanding of data analysis and reporting.
+Excellent organizational and time-management skills.
+Good communication skills, both written and verbal.
+Ability to work independently and manage time effectively.
+A proactive approach to problem-solving.
 """
 
 # Run inference
@@ -74,15 +82,16 @@ for ent in entities:
 **Example Output:**
 
 ```
-ROLE       | Intern                   | score=0.991
-SKILL      | design                   | score=0.874
-SKILL      | develop                  | score=0.862
-SKILL      | implement                | score=0.849
-SKILL      | AI agents                | score=0.921
-SKILL      | Python                   | score=0.982
-SKILL      | TensorFlow               | score=0.976
-SKILL      | PyTorch                  | score=0.973
-DISCIPLINE | AI                       | score=0.955
+Device set to use cpu
+Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.
+SKILL      |  detail                   | score=1.000
+SKILL      |  Excel                    | score=1.000
+SKILL      |  management               | score=1.000
+SKILL      |  data analysis            | score=1.000
+SKILL      |  reporting                | score=1.000
+SKILL      |  time                     | score=0.993
+SKILL      | management                | score=1.000
+SKILL      |  communication skills     | score=1.000
 ```
 
 ---