Local README example just gives "Aborted"
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 12.5k
- Forks
- 998
- Avg merge
- 3d 13h
- Merged PRs (30d)
- 10
Description
I have worked through the README's Installing on own machine, but when I now launch either
llm -m llama2 'difference between a llama and an alpaca'
or
llm chat -m llama2
, I only get Aborted.
How can I find out what the problem ist?
Would it be possible to get a better error message here?
I have got this machine (screenfetch excerpt) with 12GB VRAM:
OS: Debian 11 bullseye
Kernel: x86_64 Linux 5.10.0-21-amd64
Disk: 1,5T / 1,8T (86%)
CPU: Intel Xeon E5-2660 v3 @ 40x 3,3GHz
GPU: GeForce GTX TITAN X
RAM: 23279MiB / 128840MiB
and from nVidia:
GPU driver 460.32.03, CUDA 11.2.2, cuDNN 8.1.0,
so TensorFlow 2.9.1 runs on GPU here.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the README section “Installing a model that runs on your own machine” and reproduce the two commands shown in the issue. Trace where the command reports only Aborted; done means the failure provides a more useful explanation of the underlying problem.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, cli
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100