Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

github.com

Post reply on HN
Print view View original

61–70 of 86 posts

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#61

Post by jayshua »

stagas wrote: post #23

Tangential, maybe someone here knows; how complicated would be to implement an autocompleter that just understands syntax + patterns and can offer me suggestions but based on my own stuff? Like what is the simplest version of Copilot that doesn't require huge amounts of training but just does a decent job at recognizing tokens and trying to fill in the structure based on some input code. e.g: `app.get('/',|` {}`, may…

The latest version of Sublime Text works kind of like that. It know the tokens that most commonly appear together in the folders you currently have open in the sidebar and prioritizes the suggestions popup based on that. Seems to work pretty well for me.

It's a relatively new feature - within the last year I think.

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#62

Post by triyambakam »

stagas wrote: post #23

Tangential, maybe someone here knows; how complicated would be to implement an autocompleter that just understands syntax + patterns and can offer me suggestions but based on my own stuff? Like what is the simplest version of Copilot that doesn't require huge amounts of training but just does a decent job at recognizing tokens and trying to fill in the structure based on some input code. e.g: `app.get('/',|` {}`, may…

The plugin TabNine does what you're looking for. I've been using it enjoyably for about two years.

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#63

Post by colordrops »

triyambakam wrote: post #62
stagas wrote: post #23

Tangential, maybe someone here knows; how complicated would be to implement an autocompleter that just understands syntax + patterns and can offer me suggestions but based on my own stuff? Like what is the simplest version of Copilot that doesn't require huge amounts of training but just does a decent job at recognizing tokens and trying to fill in the structure based on some input code. e.g: `app.get('/',|` {}`, may…

The plugin TabNine does what you're looking for. I've been using it enjoyably for about two years.

It sends your code to the cloud though.

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#64

Post by ensemblehq »

moyix wrote: post #50
low_tech_punk wrote: post #12

Bravo! I'm so glad this is born. I'm curious about its model, SalesForce CodeGen. Does it train on all the public repos on GitHub? Does Copilot have access to private repos that CodeGen cannot access? Also, it would be really cool if I can personalize FauxPilot by feeding it with all my repos on GitHub. Sometimes I just need to reimplement a function I've written before but it's really hard to find where my old code…

It is possible to fine-tune CodeGen using Huggingface Transformers! Then you'd be able to fine-tune it on your own code and use the resulting model. However, training is more expensive -- you'd need an A6000 or better to train the 6B model. Something like the following should work: deepspeed --num_gpus 1 --num_nodes 1 run_clm.py --model_name_or_path=Salesforce/codegen-6B-multi --per_device_train_batch_size=1 --learni…

A friend of mine runs Sushi Cloud (https://www.sushi.cloud/), which could help make things cheaper than AWS for training purposes.

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#65

Post by Mo3 »

moyix wrote: post #50
low_tech_punk wrote: post #12

Bravo! I'm so glad this is born. I'm curious about its model, SalesForce CodeGen. Does it train on all the public repos on GitHub? Does Copilot have access to private repos that CodeGen cannot access? Also, it would be really cool if I can personalize FauxPilot by feeding it with all my repos on GitHub. Sometimes I just need to reimplement a function I've written before but it's really hard to find where my old code…

It is possible to fine-tune CodeGen using Huggingface Transformers! Then you'd be able to fine-tune it on your own code and use the resulting model. However, training is more expensive -- you'd need an A6000 or better to train the 6B model. Something like the following should work: deepspeed --num_gpus 1 --num_nodes 1 run_clm.py --model_name_or_path=Salesforce/codegen-6B-multi --per_device_train_batch_size=1 --learni…

I train models 24/7 right now and PLEASE do not use AWS for it. You're going to pay out of your backside for it.

Better alternatives: Google Colab, Paperspace Gradient, Lambdalabs Cloud, Vultr GPU instances

Colab will give you a T4, K80, V100 or P100 (alternatively their own TPUs) for free - $50 for 24h uninterrupted background jobs, Gradient will give you free A6000s and sometimes even free A100s for a $40 subscription for 6 hours (repeatable ad infinitum), Lambdalabs gives you a RTX 6000 for 0.50/hour and A6000 for 0.80/hour and Vultr GPU will give you 1/7th of an A100 for 0.37/hour

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#66

Post by triyambakam »

colordrops wrote: post #63
triyambakam wrote: post #62

Earlier quoted context omitted.

The plugin TabNine does what you're looking for. I've been using it enjoyably for about two years.

It sends your code to the cloud though.

Well, it _can_ but that option is configurable.

Re: FauxPilot – an attempt to build a locally hosted version of GitHub Copilot

#70

Post by Mo3 »

ensemblehq wrote: post #64
moyix wrote: post #50

Earlier quoted context omitted.

It is possible to fine-tune CodeGen using Huggingface Transformers! Then you'd be able to fine-tune it on your own code and use the resulting model. However, training is more expensive -- you'd need an A6000 or better to train the 6B model. Something like the following should work: deepspeed --num_gpus 1 --num_nodes 1 run_clm.py --model_name_or_path=Salesforce/codegen-6B-multi --per_device_train_batch_size=1 --learni…

A friend of mine runs Sushi Cloud ( https://www.sushi.cloud/ ), which could help make things cheaper than AWS for training purposes.

I can't see how this is relevant to the discussion. There is no mention of GPU instances in the first place.
Post reply on HN