diff options
| author | Daniel Bevenius <daniel.bevenius@gmail.com> | 2024-02-18 17:19:23 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-18 18:19:23 +0200 |
| commit | fc0c8d286a533363a9a663510b62af85ffad58b3 (patch) | |
| tree | 900a2210a71c7600acd0f8ea50847293bc4d2c3e /examples | |
| parent | bd2d4e393b2b7d2a1b2e201058e26017c9728ead (diff) | |
llava : update surgery script to not remove tensors (#5536)
This commit updates the surgery script to not remove the tensors from the
model file. For this to work the `--skip-unknown` flag is added as an
argument to the convert.py script in README.md.
The motivation for this change is that the surgery script currently
removes the projector tensors from the model file. If the model was
checked out from a repository, the model file will have been updated
and have to be checked out again to reset this effect. If this can be
avoided I think it would be preferable.
I did not perform this change for BakLLaVA models as I am not sure
how that part works.
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/llava/README.md | 2 | ||||
| -rw-r--r-- | examples/llava/llava-surgery.py | 6 |
2 files changed, 2 insertions, 6 deletions
diff --git a/examples/llava/README.md b/examples/llava/README.md index 57eb4293..e42db6e5 100644 --- a/examples/llava/README.md +++ b/examples/llava/README.md @@ -53,7 +53,7 @@ python ./examples/llava/convert-image-encoder-to-gguf.py -m ../clip-vit-large-pa 5. Use `convert.py` to convert the LLaMA part of LLaVA to GGUF: ```sh -python ./convert.py ../llava-v1.5-7b +python ./convert.py ../llava-v1.5-7b --skip-unknown ``` Now both the LLaMA part and the image encoder is in the `llava-v1.5-7b` directory. diff --git a/examples/llava/llava-surgery.py b/examples/llava/llava-surgery.py index 0a61efdf..8b7a62fb 100644 --- a/examples/llava/llava-surgery.py +++ b/examples/llava/llava-surgery.py @@ -19,10 +19,6 @@ mm_tensors = [k for k, v in checkpoint.items() if k.startswith("model.mm_project projector = {name: checkpoint[name].float() for name in mm_tensors} torch.save(projector, f"{args.model}/llava.projector") -# remove these tensors from the checkpoint and save it again -for name in mm_tensors: - del checkpoint[name] - # BakLLaVA models contain CLIP tensors in it clip_tensors = [k for k, v in checkpoint.items() if k.startswith("model.vision_tower")] if len(clip_tensors) > 0: @@ -39,7 +35,7 @@ if len(clip_tensors) > 0: f.write("{}\n") -torch.save(checkpoint, path) + torch.save(checkpoint, path) print("Done!") print(f"Now you can convert {args.model} to a regular LLaMA GGUF file.") |