Goutham Vignesh@gouthamvicky26
is under improvement
9
Events attended
2
Submissions made
AI Research Engineer
India
2 years of experience
About me
Hello, I'm Goutham Vignesh, an AI Research Engineer at Scispace. With a passion for cutting-edge technology, I specialize in training and deploying machine learning models, mainly focused on fine-tuning LLM models for different business problems. Through my expertise, I strive to leverage the power of artificial intelligence to drive innovation and solve complex challenges. With a strong background in AI research and engineering, I am dedicated to pushing the boundaries of what is possible in machine learning. Skills - Python, Pytorch, Torch serve, Fast API, Docker, MongoDB
is under improvement
.png&w=640&q=75)
🤓 Submissions
Prompt Tune Generation
Prompt Tune Generation is a prototype model which has ability to generate music using Cohere prompt by understanding the user input. Using Prompt Tune user can play with different set of Genre as input prompt to the model which will generate music notes followed by a short music clip tuned using custom virtual Keyboard which has single octave. This is one step closer diffusion based model where Generative AI plays a vital role in generating contents on its own.
Congruity - Trustworthy AI
Congruity.AI provides a diverse set of tools and options for business users and consumers alike to interrogate the consistency of content provided by large language models. It does this by first returning a varied sample of responses, utilizing different API parameters as well as prompt variation. We then ingest and analyze the results to present visualizations and other tools for users to investigate the quality and consistency of generated text. These approaches include an ngram census (portrayed on the text), similarity matrices (showing how similar responses are to one another), links to external sources for verification, and a comparison to constitutional rules or values for the language model. Using these complementary tools, users can drill down to identify elements of generated text that are consistent with the facts, with one another, and with corporate or personal values.
