AI Everyday #21 - Phind, a CodeLlama fine-tune, beating GPT4 at HumanEval
09/13/23 • 10 min
Matt discusses his results from testing Phind-CodeLlama-34B-v2, which beat the GPT-4 zero-shot HumanEval test by a good margin.
Matt discusses his results from testing Phind-CodeLlama-34B-v2, which beat the GPT-4 zero-shot HumanEval test by a good margin.
Previous Episode
AI Everyday - #20 - Llama2, GPTQ Quantization, and Text-Generation-Webui
Matt discusses Llama2 with GPTQ quantization, which is much more powerful than previous methods of quantizing model weights, and demos text-generation-webui.
Next Episode
AI Everyday #22 - BootPIG: DreamBooth-worthy image modification without fine-tuning
Matt reviews bootpig, a paper/model that provides DreamBooth-style modification of images without fine tuning.
If you like this episode you’ll love
Episode Comments
Generate a badge
Get a badge for your website that links back to this episode
<a href="https://goodpods.com/podcasts/ai-everyday-305199/ai-everyday-21-phind-a-codellama-fine-tune-beating-gpt4-at-humaneval-43449139"> <img src="https://storage.googleapis.com/goodpods-images-bucket/badges/generic-badge-1.svg" alt="listen to ai everyday #21 - phind, a codellama fine-tune, beating gpt4 at humaneval on goodpods" style="width: 225px" /> </a>
Copy