-
As explained in https://github.com/instructlab/dev-docs/pull/81. Once the introduction of vLLm (https://github.com/instructlab/instructlab/pull/1442) is merged, we need to rework the backend arguments…
leseb updated
3 months ago
-
I am trying to follow the instruction to generate/train a model with some custom knowledge. The thing is that I am using CPU and Linux training, that seems to be not working correctly. The generation…
jgato updated
2 months ago
-
*For details on how this process works, please see our [contributor roles documentation](https://github.com/instructlab/community/blob/main/CONTRIBUTOR_ROLES.md)*
**Which member are you nominating …
-
I've been working on an end-to-end CI job that includes the full SDG pipeline. I saw this exception occur in one of the test runs.
https://github.com/russellb/ilab-runner/actions/runs/9830002619/jo…
-
Currently in the `scripts/functional-tests.sh` file (and `scripts/basic-workflow-tests.sh` file too I believe, we always install `ilab` statically via `pip install .`.
While this allows us to validat…
-
It would be really useful as a dev contributor if you could quickly spin a model inference server.
Two approaches could be taken here:
1) ilab cli setup and ilab serve instructions - link to exi…
-
Changes to be made:
1) Change the section name from 'Knowledge' to 'Question and Answers'.
2) Ensure/strongly advise a minimum of 5 Q and As are provided by the user.
`Each qna.yaml file requir…
-
**Describe the bug**
https://github.com/instructlab/instructlab/pull/1471 changed the location of files to use XDG on Linux and platform directories on macOS. This is a breaking change and behavior c…
tiran updated
3 months ago
-
Similar to https://github.com/instructlab/sdg/pull/33
-
An extra `-- --tensor-parallel-size n` (n being the num of gpus) is needed in the `ilab model serve` command when serving the model. This should be doc'ed in the readme. Also, we would like to point o…