kateklink
Joined 12 years ago
Karma
116
Submissions
46
Member since
Jan 25
Recent submissions
Comment · 3 years ago
for pass@1 HumanEval tells how well the model solves a task from a set, given only one chance to solve it. It's not the perfect metric, there're other like DS-1000, MBPP (we have included them on HuggingFace model card). HumanEval is good for benchmarking with other models as it gives a fast idea how powerful the model is.
Comment · 3 years ago
we want to help developers who need either on-premise or permissive code assistant, copilot has neither of this. We also wanted to lower the barriers for self-hosting, so that the model is available on most GPUs with just 3GB Ram. Plus making the code completions fast and efficient (understanding entire context, not just the previous tokens).
Comment · 3 years ago
We’ve finished training a new code model Refact LLM which took us about a month. The main use-case is for blazing-fast code completion with fill-in-the-middle, additionally, the model could reply to chat prompts.
It has much better performance than all of the code models of similar size, and almost reaches the same HumanEval as Starcoder being 10x smaller in size.
With the small size, it can work with most modern GPUs requiring just 3GB Ram.
You can try self-hosting it in Refact https://github.com/smallcloudai/refact/ and get a local fast copilot alternative with decent suggestions.
Weights and model card https://huggingface.co/smallcloudai/Refact-1_6B-fim.
We would love to hear your feedback!
Comment · 3 years ago
at Refact we have Jetbrains plugin that works with a bunch of local code models https://github.com/smallcloudai/refact/
Comment · 3 years ago
having more plugin support is in our plans for sure. We're also open for contributions.
Comment · 3 years ago
we try to eliminate this problem by using code models trained only on permissevely licensed code, then you can run them locally without sending code anywhere
Comment · 3 years ago
we're going in this direction for code models with Refact https://github.com/smallcloudai/refact/ - right now you self-host code models, fine-tune them on local files, get the model running locally inside your IDE
Comment · 3 years ago
try refact.ai they have plugin for JetBrains IDEs and support for local LLMs https://github.com/smallcloudai/refact/
Comment · 3 years ago
there's also Refact (https://github.com/smallcloudai/refact/) with support of several open-source code LLMs and extension for VS Code and Jetbrains
Comment · 3 years ago
at refact.ai we have different functions for code refactoring, making it shorter, simplifying complexity, etc
Comment · 3 years ago
Refact.Ai | https://refact.ai | Developer Advocate | Software Engineer | Remote (UK & Europe) | 80 - 120K + equity
We're building the best open-source AI for coding using all the best LLMs available in the internet (GPT, Starcoder, WizardCoder, LLama2).
We’re hiring for Refact’s first Developer Advocate. As the first Developer Advocate, you'll play a key role in helping developers use the power of AI for coding. You'll have the opportunity to grow and support a community of developers who are excited about the future of AI and open-source.
We're looking for a Software Engineer to help us build the best developer experience for the AI code assistants inside IDEs. We currently have VS Code and Jetbrains plugins and plan to add more IDEs and more functionality to the plugins.
Apply: Developer Advocate https://wellfound.com/l/2yXwiJ
Software Engineer: https://wellfound.com/l/2zdYHM