fix: Zen 3 arch naming, remove abliterated tag

README.md

@@ -8,7 +8,6 @@ tags:
 - zenlm
 - hanzo-ai
 - zen-3
-
 pipeline_tag: text-generation
 library_name: transformers
 base_model: zenlm/zen-pro
@@ -16,21 +15,19 @@ base_model: zenlm/zen-pro
 
 # Zen 3 Math
 
-> **Parameters**: 32B | **Context**: 32K | **License**: Apache 2.0 | **Released**: 2024-11-15
+> **Parameters**: 32B | **Architecture**: Zen 3 Architecture | **Context**: 32K | **License**: Apache 2.0 | **Released**: 2024-11-15
 
 Zen 3 generation label. Weights at [zenlm/zen-pro](https://huggingface.co/zenlm/zen-pro).
 
-The Zen 3 family (Q3–Q4 2024) introduced MoE sparse routing and extended the family to cover vision, audio, image generation, and multimodal reasoning.
+The Zen 3 family (Q3–Q4 2024) introduced sparse MoE routing and expanded to vision, audio, and multimodal reasoning.
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-# Weights are at the canonical repo:
 model = AutoModelForCausalLM.from_pretrained("zenlm/zen-pro", torch_dtype="auto")
 tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-pro")
 ```
 
 ```bash
-# Or via Ollama:
 ollama run hf.co/zenlm/zen-pro
 ```