frob
frob
The problem is not server crashes, it's that embeddings done in parallel are corrupted. ```console $ for p in 1 2 3 4 ; do echo parallel=$p ; seq 0...
Can you provide an example of an interaction with ollama that demonstrates the problem? ```console $ ollama -v ollama version is 0.6.6 $ ollama run deepcoder hello Hello! How can...
These are [hallucinations](https://en.wikipedia.org/wiki/Hallucination_\(artificial_intelligence\)), they are a by-product of the probabilistic token generation that large language models do. The questions/support cases are drawn from the data the model was trained with.
https://github.com/ollama/ollama/issues/3582
The log is from version 0.5.7 of ollama, which only compiles runners with AVX/AVX2 extensions.
0.5.8+ starts a basic CPU runner that then dynamically loads libraries for dealing with extended CPU architectures or GPUs. If you set `OLLAMA_DEBUG=1` in the server environment and post the...
``` time=2025-02-14T21:48:31.757-05:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-02-14T21:48:31.757-05:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=72 time=2025-02-14T21:48:31.757-05:00 level=DEBUG source=ggml.go:89 msg="ggml backend...
https://github.com/ollama/ollama/pull/9203 1. Can you quantify "slow down?" 2. `ollama --verbose` is the best that ollama can offer.
Is there any particular prompt that causes garbled output? During short or long query/response? Do you have continuous sessions (ie, multiple queries/responses)? If so, does the garbled output happen later...
It sounds like you are running in to a context size issue - one session, and when it gets garbled it stays that way until restarted. The only point against...