fix: Zen 2 arch naming, remove abliterated tag

README.md

@@ -8,7 +8,6 @@ tags:
 - zenlm
 - hanzo-ai
 - zen-2
-
 pipeline_tag: text-generation
 library_name: transformers
 ---
@@ -16,8 +15,7 @@ library_name: transformers
 # Zen 2 7B — Code Specialist
 
 > **Originally released**: 2024-07-15
-> **Parameters**: 7B | **Architecture**: Dense transformer (Zen MoDE v2) | **Context**: 128K
-> **License**: Apache 2.0
+> **Parameters**: 7B | **Architecture**: Zen 2 Architecture | **Context**: 128K | **License**: Apache 2.0
 
 Second generation of the Zen LM family (Q2 2024). Key breakthrough: **128K context window** via improved positional encoding and sliding window attention.
 
@@ -25,13 +23,13 @@ Specialized on code generation: Python, JavaScript, TypeScript, Go, Rust, SQL.
 
 ## Research Lineage
 
-| Generation | Release | Key Advancement |
-|------------|---------|-----------------|
-| Zen 1 | Q4 2023 | Foundation, Zen MoDE v1, 4K context |
-| Zen 2 | Q2 2024 | 128K context window |
-| Zen 3 | Q3–Q4 2024 | MoE + multimodal families |
-| Zen 4 | Q1 2025 | Abliterated weights, 256K–1M ctx |
-| Zen 5 | 2025+ | Next-generation frontier |
+| Generation | Release | Architecture | Key Advancement |
+|------------|---------|--------------|-----------------|
+| Zen 1 | Q4 2023 | Zen 1 Architecture | Foundation, dense transformer, 4K context |
+| Zen 2 | Q2 2024 | Zen 2 Architecture | 128K context window |
+| Zen 3 | Q3–Q4 2024 | Zen 3 Architecture | Sparse MoE routing, multimodal |
+| Zen 4 | Q1 2025 | Zen 4 Architecture | 256K–1M context, extended families |
+| Zen 5 | 2025+ | Zen MoDE | Next-generation frontier |
 
 
 ---