Update README.md

README.md

@@ -1,3 +1,4 @@
+```markdown
 ---
 library_name: sentence-transformers
 pipeline_tag: sentence-similarity
@@ -5,78 +6,99 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
-
+- job-matching
+- skill-similarity
+- embeddings
 ---
 
-# {MODEL_NAME}
+# alvperez/skill-sim-model
+
+This is a fine-tuned [sentence-transformers](https://www.SBERT.net) model for **skill similarity** and **job matching**. It maps short skill phrases (e.g., `Python`, `Forklift Operation`, `Electrical Wiring`) into a 768-dimensional embedding space, where semantically related skills are closer together.
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+It can be used for:
 
-<!--- Describe your model here -->
+- Matching candidates to job requirements
+- Measuring similarity between skills
+- Clustering and grouping skill sets
+- Resume parsing or job recommendation systems
 
-## Usage (Sentence-Transformers)
+---
 
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+## 🧪 Usage (Sentence-Transformers)
 
-```
+To use this model:
+
+```bash
 pip install -U sentence-transformers
 ```
 
-Then you can use the model like this:
-
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
+model = SentenceTransformer('alvperez/skill-sim-model')
+
+skills = ["Electrical Wiring", "Circuit Troubleshooting", "Machine Learning"]
+embeddings = model.encode(skills)
+
+print(embeddings.shape)  # (3, 768)
 ```
 
+---
+
+## 🧭 Evaluation Results
 
+The model was evaluated on a labeled skill similarity dataset using the following metrics:
 
-## Evaluation Results
+| Metric               | Value   |
+|----------------------|---------|
+| Spearman Correlation | 0.8612  |
+| ROC AUC              | 0.9127  |
 
-<!--- Describe how your model was evaluated -->
+These scores indicate strong alignment with human-labeled skill similarity ratings.
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+---
 
+## 🧠 Training Details
 
-## Training
-The model was trained with the parameters:
+The model was fine-tuned on a custom skill similarity dataset using `CosineSimilarityLoss`.
 
-**DataLoader**:
+### **DataLoader**
 
 `torch.utils.data.dataloader.DataLoader` of length 409 with parameters:
-```
+
+```python
 {'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
-**Loss**:
-
-`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+### **Loss**
 
-Parameters of the fit()-Method:
+```python
+sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss
 ```
+
+### **Training Parameters**
+
+```python
 {
     "epochs": 5,
     "evaluation_steps": 100,
-    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "evaluator": "EmbeddingSimilarityEvaluator",
     "max_grad_norm": 1,
-    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_class": "AdamW",
     "optimizer_params": {
         "lr": 2e-05
     },
     "scheduler": "WarmupLinear",
-    "steps_per_epoch": null,
     "warmup_steps": 100,
     "weight_decay": 0.01
 }
 ```
 
+---
 
-## Full Model Architecture
-```
+## 🧬 Model Architecture
+
+```python
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
   (1): Pooling({'word_embedding_dimension': 768, '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})
@@ -84,6 +106,11 @@ SentenceTransformer(
 )
 ```
 
-## Citing & Authors
+---
+
+## 📚 Citation & Attribution
 
-<!--- Describe where people can find more information -->
+- Model fine-tuned by [@alvperez](https://huggingface.co/alvperez)
+- Built with [Sentence-Transformers](https://www.sbert.net/)
+- Inspired by semantic search and skill-matching use cases
+```