Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

llava : update surgery script to not remove tensors (#5536)

Browse Source 
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.
This commit is contained in:
Daniel Bevenius 2024-02-18 17:19:23 +01:00 committed by GitHub
parent bd2d4e393b
commit fc0c8d286a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/llava/README.md
View File

@ -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: 5. Use `convert.py` to convert the LLaMA part of LLaVA to GGUF:
```sh ```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. Now both the LLaMA part and the image encoder is in the `llava-v1.5-7b` directory.

6
examples/llava/llava-surgery.py
View File

@ -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} projector = {name: checkpoint[name].float() for name in mm_tensors}
torch.save(projector, f"{args.model}/llava.projector") 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 # BakLLaVA models contain CLIP tensors in it
clip_tensors = [k for k, v in checkpoint.items() if k.startswith("model.vision_tower")] clip_tensors = [k for k, v in checkpoint.items() if k.startswith("model.vision_tower")]
if len(clip_tensors) > 0: if len(clip_tensors) > 0:
@ -39,7 +35,7 @@ if len(clip_tensors) > 0:
f.write("{}\n") f.write("{}\n")
torch.save(checkpoint, path) torch.save(checkpoint, path)
print("Done!") print("Done!")
print(f"Now you can convert {args.model} to a regular LLaMA GGUF file.") print(f"Now you can convert {args.model} to a regular LLaMA GGUF file.")