You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you, I ran it after installing docker docker run -ti --rm quay.io/go-skynet/llama-cli:v0.1 --instruction "What's an alpaca?" --topk 10000
I ran this command but it seems to start the process for 5-6 seconds and ends it without displaying any output,
the same thing happens in API, the localhost site doesnt even load and the process stops are 5-6 without output. Any idea what might be causing this
Thank you, I ran it after installing docker docker run -ti --rm quay.io/go-skynet/llama-cli:v0.1 --instruction "What's an alpaca?" --topk 10000 I ran this command but it seems to start the process for 5-6 seconds and ends it without displaying any output, the same thing happens in API, the localhost site doesnt even load and the process stops are 5-6 without output. Any idea what might be causing this
I was able to fix this by allocating more memory in Docker Desktop settings:
hello! thanks, it seems in windows you have to create a .wslconfig in order to increase the limits. But its working now.
II'm confused tho, the API is for LLaMa right? and not the fine-tuned alpaca models (trained on gpt-3 data).
Activity
mudler commentedon Mar 21, 2023
Hi!
I don't have a windows machine to double check, but I don't think there should be anything specific preventing it to work there.
Just install docker and start in API mode https://github.com/go-skynet/llama-cli#advanced-usage, or I guess WSL should work too.
anm5704 commentedon Mar 21, 2023
Thank you, I ran it after installing docker
docker run -ti --rm quay.io/go-skynet/llama-cli:v0.1 --instruction "What's an alpaca?" --topk 10000I ran this command but it seems to start the process for 5-6 seconds and ends it without displaying any output,
the same thing happens in API, the localhost site doesnt even load and the process stops are 5-6 without output. Any idea what might be causing this
stasadance commentedon Mar 22, 2023
I was able to fix this by allocating more memory in Docker Desktop settings:
anm5704 commentedon Mar 23, 2023
hello! thanks, it seems in windows you have to create a .wslconfig in order to increase the limits. But its working now.
II'm confused tho, the API is for LLaMa right? and not the fine-tuned alpaca models (trained on gpt-3 data).
mudler commentedon Mar 23, 2023
the api should work for both, although I've tested only alpaca models. The new version
0.3has an--alpacaboolean flag too.mudler commentedon Apr 4, 2023
I guess we can close this now? Thanks @stasadance for pointing us in the right direction!
squashmerge rf-core-3 to fresh branch, attempt mudler#2 at fighting DCO
GeorgeS2019 commentedon Nov 2, 2024
we need easy windows installation documentation
feat: cloud-proxy backend + routing + middleware stack
feat: cloud-proxy backend + routing + middleware stack
feat: cloud-proxy backend + routing + middleware stack
feat: cloud-proxy backend + routing + middleware stack
feat(distributed): resumable file uploads via HTTP Content-Range
feat(distributed): resumable file uploads via HTTP Content-Range
feat(distributed): resumable file uploads via HTTP Content-Range
feat(distributed): resumable file uploads via HTTP Content-Range
feat(distributed): resumable file uploads via HTTP Content-Range (#10109
fix(llama-cpp): re-sync carry-patches to llama.cpp 7c158fbb
docs(paged): B-2 down_proj act-quant retune RESULT - negative (no hea…
docs(paged): scope porting the portable benefits to Metal/SYCL/Vulkan…
docs(distributed): move the active carrier label off the worker boxes