GitLab

lint some of the things

local wording was confusing people -- Ollama runs on cloud providers

* add embed model command and fix question invoke

* Update docs/tutorials/langchainpy.md
Co-authored-by: Kim Hallberg <hallberg.kim@gmail.com>

* Update docs/tutorials/langchainpy.md

---------
Co-authored-by: Kim Hallberg <hallberg.kim@gmail.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* fix oneapi errors on windows 10

* Revert "use `int32_t` for call to tokenize (#4738)"

This reverts commit 763bb65d.

* Revert "vocab only"

This reverts commit bf54c845.

* Revert "use ffi for tokenizing/detokenizing"

This reverts commit 26a00a04.

added IsValidNamespace function

* use `int32_t` for call to tokenize

* variable naming

* cleanup

* fix crash

vocab only for tokenize

only generate on relevant changes

* partial offloading: allow flash attention and disable mmap

* allow mmap with num_gpu=0

fixed japanese characters deleted at end of line

* update llama.cpp submodule to `5921b8f089d3b7bda86aac5a66825df6a6c10603`

* add patch

Add isolated gpu test to troubleshooting

* envconfig/config.go: Fix wrong description of OLLAMA_LLM_LIBRARY
Signed-off-by: Lei Jitang <leijitang@outlook.com>

* serve: Add more env to help message of ollama serve

Add more enviroment variables to `ollama serve --help`
to let users know what can be configurated.
Signed-off-by: Lei Jitang <leijitang@outlook.com>

---------
Signed-off-by: Lei Jitang <leijitang@outlook.com>

check if name exists before create/pull/copy

update delete handler to use model.Name