GitLab

This changes the registry client to reuse the original download URL
it gets on the first redirect response for all subsequent requests,
preventing thundering herd issues when hot new LLMs are released.

add template validation to modelfile

this change is triggered by the presence of "suffix", particularly
useful for code completion tasks

Previously, some costly things were causing the loading of GGUF files
and their metadata and tensor information to be VERY slow:

  * Too many allocations when decoding strings
  * Hitting disk for each read of each key and value, resulting in a
    not-okay amount of syscalls/disk I/O.

The show API is now down to 33ms from 800ms+ for llama3 on a macbook pro
m3.

This commit also prevents collecting large arrays of values when
decoding GGUFs (if desired). When such keys are encountered, their
values are null, and are encoded as such in JSON.

Also, this fixes a broken test that was not encoding valid GGUF.

multiple templates may appear in a model if a model is created from
another model that 1) has an autodetected template and 2) defines a
custom template

particularly useful for zipfiles and f16s

- FROM /path/to/{safetensors,pytorch}
- FROM /path/to/fp{16,32}.bin
- FROM model:fp{16,32}