Restructure: move gemma-1.1-2b to subfolder

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.spm filter=lfs diff=lfs merge=lfs -text
 gemma-3n-E2B-it-litert-preview/gemma-3n-E2B-it-int4.task filter=lfs diff=lfs merge=lfs -text
+gemma-1.1-2b/tokenizer.spm filter=lfs diff=lfs merge=lfs -text

gemma-1.1-2b/LICENSE

@@ -0,0 +1,56 @@
+# Gemma Terms of Use
+
+This folder contains the Gemma 1.1 2B Instruction-Tuned model, which is governed by Google's Gemma Terms of Use.
+
+## License
+
+The Gemma model files in this directory are provided under and subject to the **Gemma Terms of Use**.
+
+**Full Terms**: https://ai.google.dev/gemma/terms
+
+## Usage Terms Summary
+
+By downloading or using the Gemma model files from this repository, you agree to:
+
+1. **Attribution**: Include this license notice with any distribution
+2. **Prohibited Uses**: Not use for prohibited purposes (see full terms)
+3. **Compliance**: Comply with all applicable laws
+4. **Modifications**: Mark any modifications clearly
+5. **No Warranty**: Model provided "AS IS" without warranties
+
+## Model Files
+
+- **gemma-1.1-2b-it-gpu-int4.bin** (1.35 GB) - Gemma 1.1 2B IT model, INT4 quantized
+- **tokenizer.spm** (4.2 MB) - SentencePiece tokenizer
+
+## Copyright
+
+Copyright © Google LLC. All rights reserved.
+
+## Model Information
+
+- **Model Name**: Gemma 1.1 2B IT (Instruction-Tuned)
+- **Quantization**: INT4 for mobile deployment
+- **Format**: TFLite-compatible binary
+- **Target Platform**: Android/Mobile (MediaPipe)
+- **Source**: https://ai.google.dev/gemma
+
+## Important Notes
+
+1. **This is NOT an Apache 2.0 licensed model** - Gemma has its own terms
+2. **Commercial use is allowed** but subject to Gemma Terms restrictions
+3. **You must read the full terms** before using: https://ai.google.dev/gemma/terms
+4. **Attribution required**: You must acknowledge use of Gemma in your application
+
+## Disclaimer
+
+This repository distributes the Gemma model for use in the M.AI application. The model is created and owned by Google LLC. This repository's maintainer makes no warranties about the model and is not responsible for how you use it. You are solely responsible for compliance with the Gemma Terms of Use.
+
+## Questions
+
+- **Gemma Terms Questions**: Contact Google LLC
+- **Repository Questions**: https://huggingface.co/CgrHello/mai-models or https://github.com/adaflexer/mai-models/issues
+
+---
+
+**IMPORTANT**: You MUST review and agree to the complete Gemma Terms of Use before using this model: https://ai.google.dev/gemma/terms

gemma-1.1-2b/MODEL_INFO.md

@@ -0,0 +1,16 @@
+# Gemma 1.1 2B IT Model Files
+
+## Files
+- `gemma-1.1-2b-it-gpu-int4.bin` (1.35 GB) - Main model
+- `tokenizer.spm` (4.2 MB) - SentencePiece tokenizer
+
+## Checksums (SHA-256)
+See checksums.txt
+
+## Verification
+```bash
+sha256sum -c checksums.txt
+```
+
+## License
+Gemma Terms of Use: https://ai.google.dev/gemma/terms

gemma-1.1-2b/checksums.txt

@@ -0,0 +1,2 @@
+53f7defdb5554dd517a6863d2d605a144d14361d6c486bbeaac2870497b75747  gemma-1.1-2b-it-gpu-int4.bin
+61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2  tokenizer.spm

gemma-1.1-2b/gemma-1.1-2b-it-gpu-int4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f7defdb5554dd517a6863d2d605a144d14361d6c486bbeaac2870497b75747
+size 1346502656

gemma-1.1-2b/tokenizer.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003