mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-31 15:10:16 +01:00
e00d2a62dd
* llava: add requirements.txt and update README.md This commit adds a `requirements.txt` file to the `examples/llava` directory. This file contains the required Python packages to run the scripts in the `examples/llava` directory. The motivation of this to make it easier for users to run the scripts in `examples/llava`. This will avoid users from having to possibly run into missing package issues if the packages are not installed on their system. Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com> * llava: fix typo in llava-surgery.py output Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com> --------- Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
import argparse
|
|
import glob
|
|
import os
|
|
import torch
|
|
|
|
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("-m", "--model", help="Path to LLaVA v1.5 model")
|
|
args = ap.parse_args()
|
|
|
|
# find the model part that includes the the multimodal projector weights
|
|
path = sorted(glob.glob(f"{args.model}/pytorch_model*.bin"))[-1]
|
|
checkpoint = torch.load(path)
|
|
|
|
# get a list of mm tensor names
|
|
mm_tensors = [k for k, v in checkpoint.items() if k.startswith("model.mm_projector")]
|
|
|
|
# store these tensors in a new dictionary and torch.save them
|
|
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:
|
|
clip = {name.replace("vision_tower.vision_tower.", ""): checkpoint[name].float() for name in clip_tensors}
|
|
torch.save(clip, f"{args.model}/llava.clip")
|
|
|
|
# remove these tensors
|
|
for name in clip_tensors:
|
|
del checkpoint[name]
|
|
|
|
# added tokens should be removed to be able to convert Mistral models
|
|
if os.path.exists(f"{args.model}/added_tokens.json"):
|
|
with open(f"{args.model}/added_tokens.json", "w") as f:
|
|
f.write("{}\n")
|
|
|
|
|
|
torch.save(checkpoint, path)
|
|
|
|
print("Done!")
|
|
print(f"Now you can convert {args.model} to a regular LLaMA GGUF file.")
|
|
print(f"Also, use {args.model}/llava.projector to prepare a llava-encoder.gguf file.")
|