-
Notifications
You must be signed in to change notification settings - Fork 115
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
playground tests #96
playground tests #96
Conversation
3efcf80
to
e68f7e0
Compare
The following test throws an error which I'm still debugging:
|
e68f7e0
to
2a32a54
Compare
3f69279
to
bad157b
Compare
ebc1242
to
7263321
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think this makes sense. Overall comment is it could use a brief high level architecture description (possibly in the Makefile?) or a separate readme.md.
645d10d
to
0be53af
Compare
@MichaelClifford PTAL |
f218203
to
c590fe6
Compare
Signed-off-by: Liora Milbaum <[email protected]>
Signed-off-by: sallyom <[email protected]>
playground/Makefile
Outdated
pip install -r playground/tests/requirements.txt | ||
|
||
.PHONY: run | ||
run: install models/llama-2-7b-chat.Q5_K_S.gguf |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
run: install models/llama-2-7b-chat.Q5_K_S.gguf | |
run: install download |
playground/Makefile
Outdated
pip install -r playground/tests/requirements.txt | ||
|
||
.PHONY: run | ||
run: install models/llama-2-7b-chat.Q5_K_S.gguf |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is there a way to check if the model exists before downloading it? We don't want people re-downloading the model each time the use make run
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes. It is possible. I would prefer implementing it in a followup PR if that is not a critical change.
playground/Makefile
Outdated
podman build -f playground/Containerfile -t ghcr.io/ai-lab-recipes/playground --format docker playground | ||
|
||
models/llama-2-7b-chat.Q5_K_S.gguf: | ||
curl -s -S -L -f https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_S.gguf -z $@ -o [email protected] && mv -f [email protected] $@ 2>/dev/null || rm -f [email protected] $@ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we use this instead? https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF/resolve/main/mistral-7b-v0.1.Q2_K.gguf
Its smaller model (3gb) and has an apache license.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
That is doable. But, I would prefer implementing it on a followup PR.
45fa1ea
to
297fab2
Compare
Signed-off-by: Liora Milbaum <[email protected]>
297fab2
to
f31feca
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!! Thank you @lmilbaum this is really great and so much work to keep updating with the repo restructuring!!
No description provided.