cite this model
@misc {yuanz_2024,
author = { {yuanz} },
title = { llava_qwen15-4b-chat_openai-clip-vit-large-patch14-336 (Revision 5070a27) },
year = 2024,
url = { https://huggingface.co/yuanzhoulvpi/llava_qwen15-4b-chat_openai-clip-vit-large-patch14-336 },
doi = { 10.57967/hf/3146 },
publisher = { Hugging Face }
}
从0到1训练一个定制版的llava模型
- 基于openai/clip-vit-large-patch14-336 和Qwen1.5-4B-Chat模型,构建一个llava模型
- 使用数据liuhaotian/LLaVA-CC3M-Pretrain-595K
- 训练方式是deepspeed-zero2、lora进行微调。
关联的github
关联的b站学习视频
- 待填充
推理代码
from transformers import LlavaForConditionalGeneration, AutoProcessor
import torch
from PIL import Image
raw_model_name_or_path = "yuanzhoulvpi/llava_qwen15-4b-chat_openai-clip-vit-large-patch14-336"
model = LlavaForConditionalGeneration.from_pretrained(raw_model_name_or_path,device_map="cuda:0", torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained(raw_model_name_or_path)
model.eval()
print('ok')
testdata = (
'<image>\nRelay a brief, clear account of the picture shown.', # 提问
'large kitchen island with an overhang and dining space next to it', # 真实答案
'data/liuhaotian/LLaVA-CC3M-Pretrain-595K/images_dl/GCC_train_001899387.jpg' # 图片路径
)
def build_model_input(model, processor, testdata:tuple):
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": testdata[0]},
]
prompt = processor.tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
# print(prompt)
# print("*"*20)
image = Image.open(testdata[2])
inputs = processor(text=prompt, images=image, return_tensors="pt")
for tk in inputs.keys():
inputs[tk] = inputs[tk].to(model.device)
generate_ids = model.generate(**inputs, max_new_tokens=20)
generate_ids = [
oid[len(iids):] for oid, iids in zip(generate_ids, inputs.input_ids)
]
gen_text = processor.batch_decode(generate_ids, skip_special_tokens=False, clean_up_tokenization_spaces=False)[0]
return gen_text
build_model_input(model, processor, testdata)
# 'the kitchen is a bright yellow with a glass top island and a large window that looks out to the'
- Downloads last month
- 24
Inference API (serverless) does not yet support transformers models for this pipeline type.