GitLab

- re-use previously evaluated embeddings when possible
- change embeddings digest identifier to be based on model name and embedded file path

Add tutorials for using Langchain with ollama

Signed-off-by: Matt Williams <m@technovangelist.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

ggml: fix off by one error

remove used Unknown FileType

Signed-off-by: Matt Williams <m@technovangelist.com>

Document num_gqa parameter

s/parmeter/parameter/

Co-authored-by: Michael Yang <mxyng@pm.me>

implement loading ggml lora adapters through the modelfile

Decode ggml 2: Use decoded values

partial decode ggml bin for more info

It is required to be adjusted for some models, see https://github.com/jmorganca/ollama/issues/320 for more context

no warning on comments

fix could not convert int