simonw / simonw/llm

Kernel dies when using llama-2-13b

Open
#360 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
12.5k
Forks
991
Avg merge
3d 13h
Merged PRs (30d)
10

Description

I'm trying to run a python notebook with this version of llama: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF/resolve/main/llama-2-13b-chat.Q5_0.gguf

but I keep running into the issue "The Kernel crashed while executing code in the the current cell or a previous cell." When I try running a prompt on the CLI, I receive no output. Both of these examples work fine using https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q8_0.gguf

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the crash with the linked Llama-2-13B GGUF model in the Python notebook and on the CLI, then compare both results with the working 7B model. Done means the 13B model produces output without crashing the kernel in both usage paths.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, python
Domain
ai, cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.