docs: library_name: gguf, correct license, base_model link

Aligning LetheanNetwork/lemma frontmatter with the lemer pattern so HF's
llama.cpp/Ollama manifest endpoint routes pull requests correctly and
the repo surfaces in Gemma 4 gguf discovery.

Changes:
- library_name: transformers → gguf
- license: eupl-1.2 → apache-2.0 (these are unmodified Google bases,
the Gemma Terms of Use apply, not our EUPL — EUPL applies to the
LEK-modified weights in lthn/lemma)
- pipeline_tag normalised to image-text-to-text
- base_model: google/gemma-4-*-it reference added where missing
- tags: gemma4, gguf, safetensors, llama.cpp, ollama, multimodal

Co-Authored-By: Virgil <virgil@lethean.io>

README.md

@@ -1,10 +1,17 @@
 ---
-library_name: transformers
+library_name: gguf
 license: apache-2.0
 license_link: https://ai.google.dev/gemma/docs/gemma_4_license
-pipeline_tag: any-to-any
+pipeline_tag: image-text-to-text
 base_model:
-- google/gemma-4-E4B-it
+  - google/gemma-4-E4B-it
+tags:
+  - gemma4
+  - gguf
+  - safetensors
+  - llama.cpp
+  - ollama
+  - multimodal
 ---
 
 <div align="center">