diff options
| author | John <78893154+cmp-nct@users.noreply.github.com> | 2023-11-30 23:11:14 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-30 23:11:14 +0100 |
| commit | 33c9892af58b7b161f2a532935dcccff8c8048c6 (patch) | |
| tree | bbf758b597a28645db936641a32d30210924da01 /ggml-opencl.cpp | |
| parent | 8efa0f6ebed53c9453e6721da86fb294e5015909 (diff) | |
llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)
* ShareGPT4 compatibility (vision encoder only loading)
Load only a CLIP vision encoder (as supplied by ShareGPT finetunes)
Corrects the argument parsing for --img_mean and --img_std (which were previously not parsed but attempted to access)
Defines defaults for img_mean and img_std which are equal to the llava 1.5 CLIP encoder, so you do not have to provide them
* Update convert-image-encoder-to-gguf.py
Diffstat (limited to 'ggml-opencl.cpp')
0 files changed, 0 insertions, 0 deletions