First local LLM to Beat GPT-4 on Coding | Codellama-70B

preview_player
Показать описание
The best coding LLM is here and you can run it locally. Codellama-70B is able to beat GPT-40 on HumanEval.

LINKS:

TIMESTAMPS:
[00:00] New Code llama-70B
[01:03] Comparison to GPT-4
[02:10] How was it trained?
[03:21] Running it with Ollama
[04:35] Test it on Perplexity

All Interesting Videos:

Рекомендации по теме
Комментарии
Автор

CAN YOU PLEASE DO A VIDEO ON FINETUNING CODELLAMA WITH AWS SAGE MAKER, DETAILING THE THE DATA SET CREATION PROCESS ALSO

raghuvallikkat
Автор

How much RAM was this model using for inference on your local machine?

yunusycle
Автор

I was playing around with this model on a local build. Very buggy and it kept repeating code.

Canna_Science_and_Technology
Автор

Good sir 🎉 but I am confused. When I use codellama on browser via hugging face it fails to understand my question and has hard time staying on topic even when I use chatgpt to make the prompts. Is codellama only good at coding things, not debugging and brain storming together? I find chatgpt very helpful with that

test
Автор

what is the code production quality between a Q4 and a Q8 version? Q8 has less errors in code?

mzeinxp
Автор

Please do a video in setup localgpt for creating docker image and deployment

divvylorelearning
Автор

Is there actually any open source models that is actually good and not overhyped for views?

wayne
Автор

I tried 70B and it was an embarrassment. Hating when YouTubers click bait by saying these models are anywhere near GPT

BlayneOliver
Автор

Which version will run on a Raspberry Pi 5 8Gb?

SirHackaLt.
Автор

I have tested it and it made loads of mistakes even with basic code. GPT is much better

IrishKingzz