Update README.md

README.md

@@ -14,26 +14,25 @@ datasets:
 - Christoph911/German-legal-SQuAD
 - philschmid/test_german_squad
 ---
-# Summary
-
+# Model Details
 This repository contains the model [jphme/Llama-2-13b-chat-german](https://huggingface.co/jphme/Llama-2-13b-chat-german) in GGUF format, for fast and easy inference with llama.cpp and similar LLM inference tools.
 This model was created and trained by [jphme](https://huggingface.co/jphme). It is a fine-tuned variant of Meta's [Llama2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) with a compilation of multiple instruction datasets in German language. 
 
-## Model Profile (AIML)
+## Profile (.aiml)
 
-**What is an AIML Profile?**
-AIML stands for **AI Markdown Language *(.aiml)***. It is a novel description format for AI models that aims to make deployments and inference of any AI models platform-agnostic and more convenient.
+**What is AIML?**
+AIML, or AI Markdown Language (.aiml), is a novel description format designed to streamline AI model deployments. It makes the process of running AI models platform-agnostic, more easy and considerably straightforward.
 
-**What does the *config.aiml* File do?**
-Any model that is shipped with a *config.aiml* file provides all the necessary rules, information and configuration parameters to deploy AI models within your computing environment in a scalable and secure fashion.
+**Why the *config.aiml* file?**
+The presence of a *config.aiml* file within an AI model repository equips users with all the essential configuration, metadata and rules required to deploy and execute the model securely and efficiently within your computing environment.
 
-**What's the purpose?**
-The aim of *AIML* is to unify and standardize the procedure of deploying, running and maintaining AI models, which enables you to run AI services.
+**What's the purpose of AIML?**
+AIML's primary goal is to unify and simplify the steps involved in deploying, operating, and managing AI models.
 
 
-## AIML Profile
+### config.aiml
 
-### Model Overview
+### Overview
 |Attribute|Details|
 |----------------------------|--------------------------------------------------------------------------------------------------------------|
 | **ID**                     | 1                                                                                                            |
@@ -41,7 +40,7 @@ The aim of *AIML* is to unify and standardize the procedure of deploying, runnin
 | **Creator**                | [jphme](https://huggingface.co/jphme)                                                                        |
 | **Source URL**             | https://huggingface.co/                                                                                      |
 
-### Model Specifications
+### Specifications
 |Attribute|Details|
 |----------------------------|--------------------------------------------------------------------------------------------------------------|
 | **Type**                   | Large Language Model                                                                                         |
@@ -61,11 +60,13 @@ The aim of *AIML* is to unify and standardize the procedure of deploying, runnin
 | **Datasets**               | {"[Prorietary German Conversation Dataset](https://placeholder.ocal/dataset)", "[German & German legal SQuAD](https://placeholder.local/dataset)" |
 | **Notes**                  | The datasets were augmented with rows containing "wrong" contexts, in order to improve factual RAG performance. |
 
-### Run model
+### Run Instructions
+|Attribute|Details|
 | **Start Model**            | #/bin/sh<br/>chmod +x run.sh && ./run.sh <br/># This is an example. Functioning run.sh Script to be published soon |
+| **Stop Model** | # Coming soon, todo |
 
 
-## Replicate
+## Deploy from source
 1. Clone and install llama.cpp *(Commit: 9e20231)*.
 ```
 # Install llama.cpp by cloning the repo from Github.