Update model card

README.md

@@ -0,0 +1,87 @@
+---
+license: gemma
+pipeline_tag: image-text-to-text
+base_model: INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0
+tags:
+  - gemma3
+  - uk
+  - ukrainian
+  - gguf
+language:
+  - uk
+  - en
+---
+
+# MamayLM-Gemma-3-27B-IT-v2.0-GGUF
+
+GGUF quantized versions of [MamayLM-Gemma-3-27B-IT-v2.0](https://huggingface.co/INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0) for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible tools. MamayLM v2.0 is a series of Ukrainian-adapted LLMs based on Gemma 3, developed by [INSAIT](https://insait.ai).
+
+**Blog post**: [MamayLM v2.0 Release](https://models.mamay.ai/blog/mamaylm-v2-release-en/)
+
+### Key improvements over MamayLM v1.0
+
+1. **Vision-language understanding** — The model understands both text and images within the same context.
+2. **Instruction-following** — Trained on a broader range of tasks, multi-turn conversations, complex instructions, and system prompts.
+3. **Longer context** — Effective context of 131k tokens for longer conversations and complex instructions.
+4. **Updated knowledge cut-off** — Pretraining data up to May 2025, instruction fine-tuning up to October 2025.
+
+## Available quantizations
+
+| Filename | Quant type | Description |
+|----------|-----------|-------------|
+| `MamayLM-Gemma-3-27B-IT-v2.0-Q4_K_M.gguf` | Q4_K_M | Good balance of quality and size — **recommended** |
+| `MamayLM-Gemma-3-27B-IT-v2.0-Q5_K_M.gguf` | Q5_K_M | High quality, slightly larger |
+| `MamayLM-Gemma-3-27B-IT-v2.0-Q6_K.gguf` | Q6_K | Very high quality, near lossless |
+| `MamayLM-Gemma-3-27B-IT-v2.0-Q8_0.gguf` | Q8_0 | Essentially lossless |
+
+## Usage
+
+### llama.cpp
+
+```bash
+# Download a specific quantization
+huggingface-cli download INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0-GGUF \
+    --include "MamayLM-Gemma-3-27B-IT-v2.0-Q4_K_M.gguf" \
+    --local-dir .
+
+# Run with llama-cli
+llama-cli -m MamayLM-Gemma-3-27B-IT-v2.0-Q4_K_M.gguf \
+    -p "Коли був заснований Київський університет?" \
+    -n 512
+```
+
+### Ollama
+
+Create a `Modelfile`:
+
+```
+FROM ./MamayLM-Gemma-3-27B-IT-v2.0-Q4_K_M.gguf
+```
+
+Then:
+
+```bash
+ollama create mamaylm-gemma3-27b-v2.0 -f Modelfile
+ollama run mamaylm-gemma3-27b-v2.0
+```
+
+### LM Studio
+
+Search for `MamayLM-Gemma-3-27B-IT-v2.0-GGUF` in the model browser, or download a GGUF file manually and load it.
+
+## Download
+
+```bash
+# Download all quantizations
+huggingface-cli download INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0-GGUF
+
+# Download a specific file
+huggingface-cli download INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0-GGUF \
+    --include "MamayLM-Gemma-3-27B-IT-v2.0-Q4_K_M.gguf" \
+    --local-dir .
+```
+
+
+## License
+
+MamayLM-Gemma-3-27B-IT-v2.0-GGUF is distributed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).