mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-13 14:29:52 +00:00
3071c0a5f2
* 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 * clip : style changes * del common.h in clip * fix Type-Check error * fix Type-Check error * fix Type-Check error * fix Type-Check error * fix makefile error * fix ubuntu-make error * try fix clip * try fix 1 --------- Co-authored-by: Hongji Zhu <fireyoucan@gmail.com> Co-authored-by: harvestingmoon <leewenyeong@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
48 lines
2.0 KiB
Python
48 lines
2.0 KiB
Python
import argparse
|
|
import os
|
|
import torch
|
|
from transformers import AutoModel, AutoTokenizer
|
|
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("-m", "--model", help="Path to MiniCPM-V-2.5 model")
|
|
args = ap.parse_args()
|
|
|
|
# find the model part that includes the the multimodal projector weights
|
|
model = AutoModel.from_pretrained(args.model, trust_remote_code=True, local_files_only=True)
|
|
checkpoint = model.state_dict()
|
|
|
|
# get a list of mm tensor names
|
|
mm_tensors = [k for k, v in checkpoint.items() if k.startswith("resampler")]
|
|
|
|
# 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}/minicpmv.projector")
|
|
|
|
clip_tensors = [k for k, v in checkpoint.items() if k.startswith("vpm")]
|
|
if len(clip_tensors) > 0:
|
|
clip = {name.replace("vpm.", ""): checkpoint[name].float() for name in clip_tensors}
|
|
torch.save(clip, f"{args.model}/minicpmv.clip")
|
|
|
|
# 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")
|
|
|
|
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",
|
|
"AutoModelForCausalLM": "modeling_minicpm.MiniCPMForCausalLM",
|
|
"AutoModelForSeq2SeqLM": "modeling_minicpm.MiniCPMForCausalLM",
|
|
"AutoModelForSequenceClassification": "modeling_minicpm.MiniCPMForSequenceClassification"
|
|
}
|
|
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.")
|
|
print(f"Also, use {args.model}/minicpmv.projector to prepare a minicpmv-encoder.gguf file.")
|