Update README.md

README.md

@@ -1,86 +1,86 @@
----
-license: other
-license_name: proprietary
-license_link: https://huggingface.co/AbteeXAILab/lumynax-infused-gemma-e4b/resolve/main/LICENSE.txt
-library_name: transformers
-pipeline_tag: image-text-to-text
-language:
-- en
-- mi
-tags:
-- lumynax
-- lumynax-infused-gemma-e4b
-- gemma-4-e4b
-- multimodal
-- reasoning
-- audio
-- image
-- abteex-ai-labs
-- local-first
----
-
-# LumynaX Infused Gemma E4B Model
-
-LumynaX Infused Gemma E4B Model is a real local release package built around the official
-`google/gemma-4-E4B-it` checkpoint, laid out in the same top-level structure as the checked-in
-Tiny and NZ 3B releases.
-
-## Provenance
-
-- upstream base model: `google/gemma-4-E4B-it`
-- package identity: `LumynaX Infused Gemma E4B Model` from `AbteeX AI Labs`
-- important limit: this is **not** a LumynaX fine-tuned checkpoint and **not** a LumynaX-merged Gemma checkpoint
-
-## Capabilities
-
-- reasoning mode: `enabled`
-- supported modalities from the upstream base model: `text, image, audio`
-- local runtime: Transformers-based package with the real upstream weights inside `merged_model/`
-- hardcoded package identity: `merged_model/chat_template.jinja` injects the LumynaX runtime identity by default
-
-## Included Local Structure
-
-- `merged_model/`: real packaged upstream Gemma 4 E4B model files
-- `merged_model/LUMYNAX_PACKAGE_IDENTITY.txt`: packaged identity prompt for the LumynaX runtime wrapper
-- `artifacts/release_training_summary.json`: release metadata and provenance summary
-- `hf_space/`: private reasoning + multimodal Gradio demo aligned to this release package
-- `ollama/`: included for parity with other releases, but not validated for this multimodal base package
-- `release_export_manifest.json`: local manifest for this package
-
-## Important Limit
-
-This package carries the real upstream Gemma 4 E4B weights, but it does not claim any
-LumynaX-specific adaptation of those weights.
-It should be treated as a locally packaged LumynaX-branded Gemma base release under the
-`LumynaX Infused Gemma E4B Model` release identity, not as a
-true LumynaX-infused checkpoint.
-
-## Quick Start
-
-```bash
-pip install -r requirements.txt
-python quickstart.py
-python quickstart.py --mode image --image path-or-url
-python quickstart.py --mode audio --audio path-or-url
-```
-
-The default `python quickstart.py` path exercises a local text + reasoning flow.
-
-## Consumer Runtimes
-
-### Ollama
-
-The package keeps an `ollama/` folder so the release shape stays close to the existing Tiny and NZ 3B exports.
-That path has **not** been validated for this multimodal base package.
-
-```bash
-ollama create lumynax-infused-gemma-e4b -f ollama/Modelfile
-ollama run lumynax-infused-gemma-e4b
-```
-
-### Zero-Install Browser Demo
-
-The included `hf_space/` bundle is a private reasoning + multimodal Gradio demo for this package.
-Recommended default Hugging Face model repo id:
-
-- `AbteeXAILab/lumynax-infused-gemma-e4b`
+---
+license: other
+license_name: proprietary
+license_link: https://huggingface.co/AbteeXAILab/lumynax-infused-gemma-e4b/resolve/main/LICENSE.txt
+library_name: transformers
+pipeline_tag: image-text-to-text
+language:
+- en
+- mi
+tags:
+- lumynax
+- lumynax-infused-gemma-e4b
+- gemma-4-e4b
+- multimodal
+- reasoning
+- audio
+- image
+- abteex-ai-labs
+- local-first
+---
+
+# LumynaX Infused Gemma E4B Model
+
+LumynaX Infused Gemma E4B Model is a local release package built around the official
+`google/gemma-4-E4B-it` checkpoint, laid out in the same top-level structure as the checked-in
+Tiny and NZ 3B releases.
+
+## Provenance
+
+- upstream base model: `google/gemma-4-E4B-it`
+- package identity: `LumynaX Infused Gemma E4B Model` from `AbteeX AI Labs`
+- important limit: this is **not** a LumynaX fine-tuned checkpoint and **not** a LumynaX-merged Gemma checkpoint
+
+## Capabilities
+
+- reasoning mode: `enabled`
+- supported modalities from the upstream base model: `text, image, audio`
+- local runtime: Transformers-based package with the real upstream weights inside `merged_model/`
+- hardcoded package identity: `merged_model/chat_template.jinja` injects the LumynaX runtime identity by default
+
+## Included Local Structure
+
+- `merged_model/`: packaged upstream Gemma 4 E4B model files
+- `merged_model/LUMYNAX_PACKAGE_IDENTITY.txt`: packaged identity prompt for the LumynaX runtime wrapper
+- `artifacts/release_training_summary.json`: release metadata and provenance summary
+- `hf_space/`: private reasoning + multimodal Gradio demo aligned to this release package
+- `ollama/`: included for parity with other releases, but not validated for this multimodal base package
+- `release_export_manifest.json`: local manifest for this package
+
+## Important Limit
+
+This package carries the real upstream Gemma 4 E4B weights, but it does not claim any
+LumynaX-specific adaptation of those weights.
+It should be treated as a locally packaged LumynaX-branded Gemma base release under the
+`LumynaX Infused Gemma E4B Model` release identity, not as a
+true LumynaX-infused checkpoint.
+
+## Quick Start
+
+```bash
+pip install -r requirements.txt
+python quickstart.py
+python quickstart.py --mode image --image path-or-url
+python quickstart.py --mode audio --audio path-or-url
+```
+
+The default `python quickstart.py` path exercises a local text + reasoning flow.
+
+## Consumer Runtimes
+
+### Ollama
+
+The package keeps an `ollama/` folder so the release shape stays close to the existing Tiny and NZ 3B exports.
+That path has **not** been validated for this multimodal base package.
+
+```bash
+ollama create lumynax-infused-gemma-e4b -f ollama/Modelfile
+ollama run lumynax-infused-gemma-e4b
+```
+
+### Zero-Install Browser Demo
+
+The included `hf_space/` bundle is a private reasoning + multimodal Gradio demo for this package.
+Recommended default Hugging Face model repo id:
+
+- `AbteeXAILab/lumynax-infused-gemma-e4b`