Add English readme

README.en.md

@@ -0,0 +1,50 @@
+---
+base_model: gordicaleksa/YugoGPT
+inference: false
+language:
+  - sr
+  - hr
+license: apache-2.0
+model_creator: gordicaleksa
+model_name: YugoGPT
+model_type: mistral
+quantized_by: Luka Secerovic
+---
+[![sr](https://img.shields.io/badge/lang-sr-green.svg)](https://huggingface.co/alkibijad/YugoGPT-GGUF/blob/main/README.md)
+[![en](https://img.shields.io/badge/lang-en-red.svg)](https://huggingface.co/alkibijad/YugoGPT-GGUF/blob/main/README.en.md)
+
+# About the model
+[YugoGPT](https://huggingface.co/gordicaleksa/YugoGPT) is currently the best open-source base 7B LLM for BCS (Bosnian, Croatian, Serbian).
+
+This repository contains the model in [GGUF](https://github.com/ggerganov/llama.cpp/tree/master) format, which is very useful for local inference, and doesn't require expensive hardware.
+
+# Versions
+The model is compressed into a couple of smaller versions. Compression drops the quality slightly, but significantly increases the inference speed.
+
+It's suggested to use the `Q4_1` version as it's the fastest one.
+
+
+| Name | Size (GB) | Note                                                                   |
+|-------|---------------|----------------------------------------------------------------------------|
+| Q4_1  | 4.55          | Weights compressed to 4 bits. The fastest version.                       |
+| q8_0  | 7.7           | Weights compressed to 8 bits.                                          |
+| fp16  | 14.5          | Weights compressed to 16 bits.                                              |
+| fp32  | 29            | Original, 32 bit weights. Not recommended to use this. |
+
+# How to run this model locally?
+## LMStudio - the easiest way ⚡️
+Install [LMStudio](https://lmstudio.ai/).
+
+- After installation, search for "alkibijad/YugoGPT":
+![Pretraga](./media/lm_studio_screen_1.png "Pretraga modela")
+- Choose a model version (recommended `Q4_1`):
+![Izaberi model](./media/lm_studio_screen_2.1.png "Izaberi model")
+- After the model finishes downloading, click on "chat" on the left side and start chatting:
+- [Optional] You can setup a system prompt, e.g. "You're a helpful assistant" or however else you want.
+![Chat](./media/lm_studio_screen_3.png "Chat")
+
+That's it!
+
+## llama.cpp - advanced 🤓
+Ako si napredan korisnik i želiš da se petljaš sa komandnom linijom i naučiš više o `GGUF` formatu, idi na [llama.cpp](https://github.com/ggerganov/llama.cpp/tree/master) i pročitaj uputstva 🙂
+If you're an advanced user and want to use CLI and learn more about `GGUF` format, go to [llama.cpp](https://github.com/ggerganov/llama.cpp/tree/master) and follow the instructions 🙂

README.md

@@ -10,6 +10,8 @@ model_name: YugoGPT
 model_type: mistral
 quantized_by: Luka Secerovic
 ---
+[![sr](https://img.shields.io/badge/lang-sr-green.svg)](https://huggingface.co/alkibijad/YugoGPT-GGUF/blob/main/README.md)
+[![en](https://img.shields.io/badge/lang-en-red.svg)](https://huggingface.co/alkibijad/YugoGPT-GGUF/blob/main/README.en.md)
 # O modelu
 [YugoGPT](https://huggingface.co/gordicaleksa/YugoGPT) je trenutno najbolji "open source" model za srpski, hvatska, bosanski... i sve ostale jezike na koje uspemo da se "podelimo" 🙂
 
@@ -37,8 +39,8 @@ Najlakši način je da se prvo instalira [LMStudio](https://lmstudio.ai/), progr
 - Izaberi neki od modela (preporučeno `Q4_1`):
 ![Izaberi model](./media/lm_studio_screen_2.1.png "Izaberi model")
 - Nakon što se model "skine", klikni na "chat" u levom delu ekrana i možeš da ćaskaš sa modelom:
-![Chat](./media/lm_studio_screen_3.png "Chat")
 - [Opciono] Možeš da podesiš "system prompt", npr. "Ti si AI asistent koji uvek želi da pomogne." ili kako god već hoćeš.
+![Chat](./media/lm_studio_screen_3.png "Chat")
 
 To je to!