[HN Gopher] FauxPilot - an open-source GitHub Copilot server ___________________________________________________________________ FauxPilot - an open-source GitHub Copilot server Author : mlboss Score : 242 points Date : 2023-03-22 17:56 UTC (5 hours ago) (HTM) web link (github.com) (TXT) w3m dump (github.com) | MayeulC wrote: | Promising. Combine that with llama or BLOOM, perhaps finetuned on | code, and perhaps your own codebase/documentation, and you cold | have an interesting solution. | jncraton wrote: | What is wrong with the CodeGen model that they are using? | | It is a reasonably large model (up to 16B params) that has | already been trained on both natural language and code. I would | expect it to underperform larger models, including GPT-3.5 and | GPT-4, but this should still be very useful for autocomplete | and boilerplate in simpler cases. It is a bit under trained | compared to Chinchilla, T5, or LLaMA, but it still performs | well. | | According to the paper[1], this model is competitive with the | largest Codex model that was the basis for Copilot originally. | | [1] https://arxiv.org/pdf/2203.13474.pdf | MayeulC wrote: | I haven't ran any of these models yet, I had just assumed | CodeGen was less performant for "understanding" prompts. You | are right that it's probably enough, especially if fine- | tuning is an option. | | Now, I wonder: as the code-base grows, how often, and how, | should such tuning take place? | bottlepalm wrote: | +1 for the name | qwerty3344 wrote: | Would love to see a side by side comparison of the completions | from this with completions from Copilot | make3 wrote: | this is likely much worse, if copilot uses gpt3.5 turbo or | gpt4. who knows though what they're actually using. | winddude wrote: | the release today for copilot X says it's using gpt4 "With | chat and terminal interfaces, support for pull requests, and | early adoption of OpenAI's GPT-4" ~ | https://github.com/features/preview/copilot-x | 5n wrote: | I'm pretty sure that the actual Copilot auto completions | are still on GPT3 for speed and cost reasons | winddude wrote: | Yes, wait list for access to copilotX | mirthflat83 wrote: | Copilot before today was based on GPT-3 | sebzim4500 wrote: | How is this possible? They don't even use the same tokens, | right? Whitespace is different IIRC. | nonethewiser wrote: | It seems "Codepilot" is being used as a general name for a coding | focused language model. A more literal interpretation of the | title suggests you can host Microsoft's model yourself, which | does not seem to be the case (unsurprisingly). | | I guess I'm just surprised to see it used this way but "coding | focused language model" doesn't exactly roll off the tongue. | RobotToaster wrote: | Could always take the facebook approach and call them CoFLaM. | circuit10 wrote: | It's called that because it's a implementation of the Copilot | API | valine wrote: | I always assumed it a name for the application of a language | model, ie I'm using this language model as a programming | copilot. Some models making better copilots than others. | syntaxing wrote: | Anyone try some quantized model with this like llama? | 1equalsequals1 wrote: | Anyone knows how this compares to Tabnine? | stuaxo wrote: | Is Tabnine still going (and is it any good?) I used to use Kite | back in the day. | 1equalsequals1 wrote: | The free version is average at best. It only really | autocompletes a line (if you're lucky). It usually | autocompletes a few characters in an expression | marcusbuffett wrote: | Copilot is a million times better then Tabnine. Tabnine was | promising, but totally stopped making any improvements to the | model after it got bought out years ago. | nu11ptr wrote: | I wonder... is MS likely going to make it harder to swap the URL | on the official copilot client in light of this? Will they | continue hosting the "competition"? | Takennickname wrote: | I'm pretty sure VS Code Extensions aren't compiled. | benatkin wrote: | They can still lock them down, like Mozilla did with Firefox | extensions... | neximo64 wrote: | VS Code is an electron app so much harder | benatkin wrote: | I don't think so, in both places have code that's running | the extensions that you can change. | circuit10 wrote: | It has existed since October 2022, so... | nu11ptr wrote: | This is the first I'm hearing of it. I wonder how many others | as well are seeing this via HN the first time? I would | imagine MS has been aware of this since more or less | inception, however, any product threat isn't really about | existence, but how viable and how well known/used it is. | anotheryou wrote: | I'd also be interested in a "bring your own OpenAI API key" | Copilot X clone if anyone knows of one :) | plaguuuuuu wrote: | I feel like that's going to be way more expensive than just | using Copilot? | | Esp since copilot is updating to GPT4 soon anyway | phantom32 wrote: | I wonder if FauxPilot's models (Salesforce Codegen family) can be | quantized and run on the CPU. I was able to run the 350M model on | my machine but it wasn't able to compete with Copilot in any way. | Salesforce claims their model is competitive with OpenAI Codex | their github description[1]. Maybe their largest 16B model is, | but I haven't been able to try it. | | [1] https://github.com/salesforce/CodeGen | ayushkaushal wrote: | We will add quantized CodeGen for fast inference on CPUs up on | cformers (https://github.com/NolanoOrg/cformers/) by later | today. | syntaxing wrote: | Whoa is there a PR or wiki about this | underlines wrote: | 4bit GPTQ maybe? | toastal wrote: | Are there alternatives that don't require an Nvidia GPU and works | with AMD? And more on-brand being hosted on a different code | forge? | tommica wrote: | So much potential in this! Would love to run this locally! ___________________________________________________________________ (page generated 2023-03-22 23:00 UTC)