bkocis

model,answer time,"token/sec",question,answer,Tokens in answer
deepseek-coder:6.7b-instruct-q2_K,46.41,3.77,Write me a simple flask application in python,"Sure! Here is a simple Flask application written in Python that returns 
""Hello, World!"" when accessing the root URL (""/""). 

Firstly, make sure to install Flask if you haven't done so yet. You can 
use pip for this purpose:
```bash
pip install flask
```
Now let's create a simple application with one route:

bkocis

model,load time,GPU memory [GB/6.7],answer time (prompt: “Write me a simple flask application in python” ,answer
deepseek-coder:1.3b-instruct-q2_K,11.74,1.6,14.72,"Sure! Here's an example of how could be done with Flask (a micro web framework for Python). This is very basic; it serves as the backend server and doesn't handle any front-end
logic. 

```python
from flask import Flask, render_template, request
app = Flask(__name__)

@app.route('/')
def home():

bkocis

<style>
      @import url(../templates/bucket.css);
    </style>
    <div id="cesiumContainer" class="fullSize"></div>
    <div id="loadingOverlay"><h1>Loading...</h1></div>
    <div id="toolbar"></div>

bkocis

var viewer = new Cesium.Viewer("cesiumContainer", {
  shouldAnimate: true,
});

var statusDisplay = document.createElement("div");
var fuelDisplay = document.createElement("div");
var czmlPath = "../SampleData/";
var vehicleEntity;

// Add a blank CzmlDataSource to hold our multi-part entity/entities.

bkocis

#!/bin/bash
#
# custom-service    Start up custom-service 
#
# chkconfig: 2345 55 25
# description: the custom service (Python)
#
# processname: custom-service

# Source function library

bkocis

AWS based projects

---

Miniproject with several branches, each testing a deployment variant of a simple page using jenkins.

• Jenkins Docker Kubernetes test

This repo contains a more detailed instructions on the setup of a jenkins server on an aws ec2 instance and runs a few tests.

• CloudDevOps-ND-Capstone

Some smaller repos with examples:

bkocis

Deep Reinforcement Learning ND:

• Navigation (Value based methods)
• Continuous Control (Policy based methods)
• Collaboration and competition (Multi-Agent Reinforcement Learning)

bkocis

https://www.alexirpan.com/2018/02/14/rl-hard.html

Prioritized Experience Learning https://github.com/jaromiru/AI-blog/blob/master/Seaquest-DDQN-PER.py

https://github.com/Ullar-Kask/TD3-PER/blob/master/Pytorch/src/PER.py https://knowledge.udacity.com/questions/46815 https://knowledge.udacity.com/questions/56910 https://knowledge.udacity.com/questions/54781

bkocis

Value based methods

Human-level control through deep reinforcement learning

Deep Reinforcement Learning with Double Q-learning

Dueling Network Architectures for Deep Reinforcement Learning

bkocis

Deep Reinforcement Learning ND:

• Collaboration and competition (Multi-Agent Reinforcement Learning)
• Continuous Control (Policy based methods)
• Navigation (Value based methods)

Computer Vision ND:

• Facial keypoint detection
• Image captioning