refact
refact copied to clipboard
AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.
mount models between host and container
Windows 11 fully updated. WSL2 updated. Docker Desktop for Windows latest , GPU works in docker. nvidia-sli reports the GPU fine. Nvidia Cuda 12.2 Toolkit Newest Nvidia drivers. RTX 3080...
Hello, I noticed a small error: A missing link on the page https://docs.refact.ai/faq/ The question: > Do you have a self-hosted option? Is answered with > Yes. Refact has a...
Llama2 (and Llama-based models) timeout. Other chat models (tested Mistral, Mixtral) respond fine. Below is the snippet of the docker container log capturing when the request is sent from Refact...
I installed refact by Docker in Server and VSCode plugin in client. Everythin works well, except when VSCode plugin try to complete. It is broken by "Cannot reach the server:...
followed the instructions, installed cuda and then ran the docker command as per docs. Error showed: docker: Error response from daemon: failed to create task for container: failed to create...
### TBD Should we add a bearer token check the the endpoint like we do with chat? ### To run add the following to the `lsp.cfg` file ``` { ......
By allowing users to rename their completed runs, they can quickly identify and distinguish between different runs. - Give names to loras when training, "all files", "only python" - what...
Use latest lora checkpoint for deepseek-coder/5.7b/mqa-base (iter0010-testloss0.683 in this example)  Try first completion. It's working:  Accept completion and press Enter:  **Expected result:** Completion is working and generating...