Update README.md

README.md

@@ -1,3 +1,46 @@
----
-license: gemma
----
+---
+library_name: gemma2.java
+license: gemma
+base_model: google/gemma-2-9b-it
+base_model_relation: quantized
+quantized_by: mukel
+tags:
+- gemma2
+- java
+- llama3.java
+- gemma2.java
+---
+
+# GGUF models for gemma2.java
+Pure .gguf `Q4_0` and `Q8_0` quantizations of Gemma 2 models, ready to consume by [gemma2.java](https://github.com/mukel/gemma2.java).
+
+In the wild, `Q8_0` quantizations are fine, but `Q4_0` quantizations are rarely pure e.g. the `output.weights` tensor is quantized with `Q6_K`, instead of `Q4_0`.  
+A pure `Q4_0` quantization can be generated from a high precision (F32, F16, BFLOAT16) .gguf source with the `llama-quantize` utility from llama.cpp as follows:
+
+```
+./llama-quantize --pure ./Gemma-2-9B-Instruct-F32.gguf ./Gemma-2-9B-Instruct-Q4_0.gguf Q4_0
+```
+
+# Gemma Model Card
+
+**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
+
+This model card corresponds to the 2b instruct version the Gemma 2 model in GGUF Format.
+
+You can also visit the model card of the [9B pretrained v2 model](https://huggingface.co/google/gemma-2-9b-it). 
+
+## Model Information
+
+Summary description and brief definition of inputs and outputs.
+
+### Description
+
+Gemma is a family of lightweight, state-of-the-art open models from Google,
+built from the same research and technology used to create the Gemini models.
+They are text-to-text, decoder-only large language models, available in English,
+with open weights, pre-trained variants, and instruction-tuned variants. Gemma
+models are well-suited for a variety of text generation tasks, including
+question answering, summarization, and reasoning. Their relatively small size
+makes it possible to deploy them in environments with limited resources such as
+a laptop, desktop or your own cloud infrastructure, democratizing access to
+state of the art AI models and helping foster innovation for everyone.