refact
refact copied to clipboard
smallcloudai
AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.
https://github.com/smallcloudai/refact/assets/140423660/47acabdd-a726-459b-bcb9-f6666abd1a6d No completion after pressing Enter and going to new line. No completion in this case even if use force completion.  Force completion works if cursor is at the...
Hi, dear: Thanks for your open source! How did you overcome the catastrophic forgetting problem in lora finetune. The performance dropped a lot on humaneval dataset after lora finetune on...
I wanted to extend my sincere appreciation for your project. As a devoted fan of your work, I have thoroughly enjoyed being part of this journey. However, I have recently...
When wanting self-hosted we are told to visit https://refact.ai/docs/self-hosting/ and run docker run -d --rm -p 8008:8008 -v perm-storage:/perm_storage --gpus all smallcloud/refact_self_hosting after ensuring we have docker with nvidia gpu...
Hi, I stumbled upon this project in search for a code generation plugin for IntelliJ that I could run locally on my Macbook Pro M3. GPT4All and LM Studio work...
hi, is there any plan to support amd gpus or even any alternatives? amd gpus have excellent vram capacity and power with reasonable price
LOGS: [watchdog_20231221.log](https://github.com/smallcloudai/refact/files/13744703/watchdog_20231221.log) I am running the containerized version of the Refact self hosting. When trying to use one of the models for chat (such as wizardlm) the chat always times...
Metadata
Owner
Metadata
AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.