Update model card: add zen/zenlm tags, fix branding

README.md

@@ -1,47 +1,65 @@
 ---
-library_name: transformers
-pipeline_tag: text-classification
+language: en
+license: apache-2.0
 tags:
-  - reranker
   - text-classification
-  - retrieval
-  - multilingual
   - zen
-  - zen3
+  - zenlm
   - hanzo
-license: apache-2.0
+  - zen3
+  - reranker
+  - retrieval
+pipeline_tag: text-classification
+library_name: transformers
 ---
 
 # Zen3 Reranker Medium
 
-**Zen LM by Hanzo AI** — Cross-encoder reranker for search result refinement and RAG pipelines. 560M parameters.
+Medium-sized Zen3 reranker for higher accuracy re-scoring in RAG pipelines.
+
+## Overview
 
-## Specs
+Built on **Zen MoDE (Mixture of Distilled Experts)** architecture with 1.5B parameters and 8K context window.
 
-| Property | Value |
-|----------|-------|
-| Parameters | 560M |
-| Context Length | 512 tokens |
-| Architecture | Zen MoDE (Mixture of Distilled Experts) |
-| Generation | Zen3 |
+Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
 
-## Usage
+## Quick Start
 
 ```python
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+model_id = "zenlm/zen3-reranker-medium"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id, torch_dtype="auto")
+
+query = "What is machine learning?"
+passages = [
+    "Machine learning is a subset of artificial intelligence...",
+    "The weather today is sunny and warm.",
+    "Neural networks learn from labeled training data.",
+]
 
-model = AutoModelForSequenceClassification.from_pretrained("zenlm/zen3-reranker-medium")
-tokenizer = AutoTokenizer.from_pretrained("zenlm/zen3-reranker-medium")
+pairs = [[query, p] for p in passages]
+features = tokenizer(pairs, padding=True, truncation=True, max_length=512, return_tensors="pt")
+
+with torch.no_grad():
+    scores = model(**features).logits.squeeze(-1)
+
+ranked = sorted(zip(scores.tolist(), passages), reverse=True)
+for score, passage in ranked:
+    print(f"Score: {score:.4f} | {passage[:80]}")
 ```
 
-## API Access
+## Model Details
 
-Available via the Hanzo AI API at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.
+| Attribute | Value |
+|-----------|-------|
+| Parameters | 1.5B |
+| Architecture | Zen MoDE |
+| Context | 8K tokens |
+| License | Apache 2.0 |
 
 ## License
 
 Apache 2.0
-
----
-
-*Zen LM is developed by [Hanzo AI](https://hanzo.ai) — Frontier AI infrastructure.*