vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llava : support MiniCPM-V-2.6 (#8967)

Browse source 
* init

* rename

* add run android for termux in readme

* add android readme

* add instructions in readme

* change name in readme

* Update README.md

* fixed line

* add result in readme

* random pos_embed

* add positions index

* change for ollama

* change for ollama

* better pos_embed in clip

* support ollama

* updata cmakelist

* updata cmakelist

* rename wrapper

* clear code

* replace and organize code

* add link

* sync master

* fix warnings

* fix warnings

* fix bug in bicubic resize when need resize iamge smaller

* receive review comments and modify

* receive review comments and modify

* put all code into llava dir

* fix quality problem in pr code

* change n_layer

* add space in "-1"

* imitate reshape bug of python code

* fix bug in clip

* fix issues for merging

* fix llama-minicpmv-cli in cmake file

* change pr readme

* fix code review

* remove in line 33 directory in the /cmakelists.txt (not in example, in the main dir

* fix cmakefile

* add warn

* fix KEY_HAS_MINICPMV_PROJ

* remove load_image_size into clip_ctx

* remove the extern "C", MINICPMV_API

* fix uhd code for review comment

* delete minicpmv-wrapper in pr

* remove uhd_image_embed

* Modify 2 notes

* support minicpmv2.6

* modify convert script of minicpmv

* modify convert

* modify convert

* add readme

* add resampler of v2.6

* modify clip

* modify readme

* fix type-check

* fix type-check

* fix type-check

* fix type-check

* modify convert script and readme

* fix convert script and readme

* fix convert

* fix num in convert

* fix type-check

---------

Co-authored-by: Hongji Zhu <fireyoucan@gmail.com>
Co-authored-by: harvestingmoon <leewenyeong@gmail.com>
This commit is contained in:
tc-mb 2024-08-16 21:34:41 +08:00 • committed by GitHub
parent ee2984bdaf
commit d565bb2fd5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 645 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/llava/minicpmv-surgery.py
View file

@ -4,7 +4,7 @@ import torch
from transformers import AutoModel, AutoTokenizer
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", help="Path to MiniCPM-V-2.5 model")
ap.add_argument("-m", "--model", help="Path to MiniCPM-V model")
args = ap.parse_args()
# find the model part that includes the the multimodal projector weights
@ -29,7 +29,6 @@ if len(clip_tensors) > 0:
f.write("{}\n")
config = model.llm.config
config._name_or_path = "openbmb/MiniCPM-Llama3-V-2.5"
config.auto_map = {
"AutoConfig": "configuration_minicpm.MiniCPMConfig",
"AutoModel": "modeling_minicpm.MiniCPMModel",
@ -40,7 +39,6 @@ config.auto_map = {
model.llm.save_pretrained(f"{args.model}/model")
tok = AutoTokenizer.from_pretrained(args.model, trust_remote_code=True)
tok.save_pretrained(f"{args.model}/model")
# os.system(f"cp {args.model}/modeling_minicpm.py {args.model}/MiniCPM_l3/modeling_minicpm.py")
print("Done!")
print(f"Now you can convert {args.model} to a regular LLaMA GGUF file.")