7 AI Portfolio Tasks to Increase the Resume – KDnuggets

I really consider that to get employed within the area of synthetic intelligence, it’s essential to have a robust portfolio. This implies it’s essential to present the recruiters that you would be able to construct AI fashions and purposes that remedy real-world issues.

On this weblog, we are going to evaluation 7 AI portfolio initiatives that may increase your resume. These initiatives include tutorials, supply code, and different supportive supplies that can assist you construct correct AI purposes.

1. Construct and Deploy your Machine Studying Software in 5 Minutes

Undertaking hyperlink: Construct AI Chatbot in 5 Minutes with Hugging Face and Gradio

Screenshot from the challenge

On this challenge, you’ll be constructing a chatbot utility and deploying it on Hugging Face areas. It’s a beginner-friendly AI challenge that requires minimal data of language fashions and Python. First, you’ll be taught numerous elements of the Gradio Python library to construct a chatbot utility, after which you’ll use the Hugging Face ecosystem to load the mannequin and deploy it. 

It’s that easy.

2. Construct AI Tasks utilizing DuckDB: SQL Question Engine

Undertaking hyperlink: DuckDB Tutorial: Constructing AI Tasks

Screenshot from the challenge

On this challenge, you’ll be taught to make use of DuckDB as a vector database for an RAG utility and likewise as an SQL question engine utilizing the LlamaIndex framework. The question will take pure language enter, convert it into SQL, and show the lead to pure language. It’s a easy and easy challenge for learners, however earlier than you dive into constructing the AI utility, it’s essential to be taught just a few fundamentals of the DuckDB Python API and the LlamaIndex framework.

3. Constructing A number of-step AI Agent utilizing the LangChain and Cohere API

Undertaking hyperlink: Cohere Command R+: A Full Step-by-Step Tutorial

Screenshot from the challenge

Cohere API is best than OpenAI API  when it comes to performance for growing AI purposes. On this challenge, we are going to discover the assorted options of Cohere API and be taught to create a multi-step AI agent utilizing the LangChain ecosystem and the Command R+ mannequin. This AI utility will take the consumer’s question, search the online utilizing the Tavily API, generate Python code, execute the code utilizing Python REPL, after which return the visualization requested by the consumer. That is an intermediate-level challenge for people with primary data and eager about constructing superior AI purposes utilizing the LangChain framework.

4. Effective-Tuning Llama 3 and Utilizing It Regionally

Undertaking hyperlink: Effective-Tuning Llama 3 and Utilizing It Regionally: A Step-by-Step Information | DataCamp

Picture from the challenge

A preferred challenge on DataCamp that may show you how to fine-tune any mannequin utilizing free sources and convert the mannequin to Llama.cpp format in order that it may be used domestically in your laptop computer with out the web. You’ll first be taught to fine-tune the Llama-3 mannequin on a medical dataset, then merge the adapter with the bottom mannequin and push the complete mannequin to the Hugging Face Hub. After that, convert the mannequin information into the Llama.cpp GGUF format, quantize the GGUF mannequin and push the file to Hugging Face Hub. Lastly, use the fine-tuned mannequin domestically with the Jan utility.

5. Multilingual Computerized Speech Recognition

Mannequin Repository: kingabzpro/wav2vec2-large-xls-r-300m-Urdu

Code Repository: kingabzpro/Urdu-ASR-SOTA

Tutorial Hyperlink: Effective-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers

Screenshot from kingabzpro/wav2vec2-large-xls-r-300m-Urdu

My hottest challenge ever! It will get nearly half 1,000,000 downloads each month. I fine-tuned the Wave2Vec2 Massive mannequin on an Urdu dataset utilizing the Transformer library. After that, I improved the outcomes of the generated output by integrating the language mannequin.

Screenshot from Urdu ASR SOTA – a Hugging Face House by kingabzpro

On this challenge, you’ll fine-tune a speech recognition mannequin in your most popular language and combine it with a language mannequin to enhance its efficiency. After that, you’ll use Gradio to construct an AI utility and deploy it to the Hugging Face server. Effective-tuning is a difficult process that requires studying the fundamentals, cleansing the audio and textual content dataset, and optimizing the mannequin coaching.

6. Constructing CI/CD Workflows for Machine Studying Operations

Undertaking hyperlink: A Newbie’s Information to CI/CD for Machine Studying | DataCamp

Picture from the challenge

One other common challenge on GitHub. It entails constructing a CI/CD pipeline or machine studying operations. On this challenge, you’ll find out about machine studying challenge templates and learn how to automate the processes of mannequin coaching, analysis, and deployment. You’ll find out about MakeFile, GitHub Actions, Gradio, Hugging Face, GitHub secrets and techniques, CML actions, and numerous Git operations. 

In the end, you’ll construct end-to-end machine studying pipelines that may run when new knowledge is pushed or code is up to date. It should use new knowledge to retrain the mannequin, generate mannequin evaluations, pull the educated mannequin, and deploy it on the server. It’s a absolutely automated system that generates logs at each step.

7. Effective-tuning Steady Diffusion XL with DreamBooth and LoRA

Undertaking hyperlink: Effective-tuning Steady Diffusion XL with DreamBooth and LoRA | DataCamp

Picture from the challenge 

We now have discovered about fine-tuning massive language fashions, however now we are going to fine-tune a Generative AI mannequin utilizing private photographs. Effective-tuning Steady Diffusion XL requires only some photos and, in consequence, you may get optimum outcomes, as proven above.

On this challenge, you’ll first find out about Steady Diffusion XL after which fine-tune it on a brand new dataset utilizing Hugging Face AutoTrain Advance, DreamBooth, and LoRA. You’ll be able to both use Kaggle free of charge GPUs or Google Colab. It comes with a information that can assist you each step of the way in which.

Conclusion

All the initiatives talked about on this weblog had been constructed by me. I made certain to incorporate a information, supply code, and different supporting supplies. 

Engaged on these initiatives provides you with helpful expertise and show you how to construct a robust portfolio, which might improve your possibilities of securing your dream job. I extremely suggest everybody to doc their initiatives on GitHub and Medium, after which share them on social media to draw extra consideration. Preserve working and hold constructing; these experiences will also be added to your resume as an actual expertise.
 
 

Abid Ali Awan (@1abidaliawan) is a licensed knowledge scientist skilled who loves constructing machine studying fashions. At the moment, he’s specializing in content material creation and writing technical blogs on machine studying and knowledge science applied sciences. Abid holds a Grasp’s diploma in expertise administration and a bachelor’s diploma in telecommunication engineering. His imaginative and prescient is to construct an AI product utilizing a graph neural community for college students combating psychological sickness.