docs: honest base_model attribution, drop marketing

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
-library_name: transformers
+base_model: Qwen/Qwen3-Embedding-8B
+library_name: sentence-transformers
 pipeline_tag: feature-extraction
 language:
 - en
@@ -11,25 +12,30 @@ tags:
 - zenlm
 - hanzo
 - embedding
+- sentence-transformers
+- retrieval
 ---
 
 # Zen Embedding 8B
 
-8B-parameter sentence-embedding model for retrieval-augmented generation, semantic search, and dense retrieval. Part of the Zen embedding family.
+8B-parameter text-embedding model for retrieval-augmented generation, semantic search, and dense retrieval. Part of the Zen embedding line.
 
-## Hosted via Hanzo gateway
+Repackaged from [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) (apache-2.0, Alibaba Qwen). Native HuggingFace `safetensors`, re-hosted under the Zen embedding line. **Not trained from scratch** — a permissively-licensed redistribution for the OSS-clean Zen model line.
 
-Served at `api.hanzo.ai` as `zen-embedding-8b`.
-
-## Files
-
-Native HuggingFace `safetensors` weights, loadable directly with `transformers`:
+## Usage
 
 ```python
-from transformers import AutoModel, AutoTokenizer
-m = AutoModel.from_pretrained("zenlm/zen-embedding-8B")
-t = AutoTokenizer.from_pretrained("zenlm/zen-embedding-8B")
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("zenlm/zen-embedding-8B")
+emb = model.encode(["The weather is lovely today.", "It's so sunny outside!"])
+print(model.similarity(emb, emb))
 ```
 
-For GGUF / Ollama deployment, see [zenlm/zen-embedding-8B-GGUF](https://huggingface.co/zenlm/zen-embedding-8B-GGUF).
+Hosted via the Hanzo gateway (`api.hanzo.ai`) as `zen-embedding-8b`.
+
+GGUF build for CPU inference: [zenlm/zen-embedding-8B-GGUF](https://huggingface.co/zenlm/zen-embedding-8B-GGUF).
+
+## License
 
+`apache-2.0`. Upstream: **Qwen/Qwen3-Embedding-8B** by Alibaba Qwen. This repository redistributes the weights under the same license.