mirror of
https://github.com/deepseek-ai/DeepSeek-VL2.git
synced 2026-11-05 01:07:23 +00:00
[GH-ISSUE #127] Simple Inference Example with Multiple Images 输出问题 #105
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-VL2#105
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @winter-JX on GitHub (Apr 6, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/127
我的相关代码
'''python
import torch
from transformers import AutoModelForCausalLM
from deepseek_vl2.models import DeepseekVLV2Processor, DeepseekVLV2ForCausalLM
from deepseek_vl2.utils.io import load_pil_images
specify the path to the model
model_path = "/data/LangXAI/llm_models/deepseek_vl2_3b"
vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer
vl_gpt: DeepseekVLV2ForCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()
multiple images/interleaved image-text
conversation = [
{
"role": "<|User|>",
"content": "This is image_1: \n"
"This is image_2: \n"
"This is image_3: \n Can you tell me what are in the images?",
"images": [
"images/multi_image_1.jpeg",
"images/multi_image_2.jpeg",
"images/multi_image_3.jpeg",
],
},
{"role": "<|Assistant|>", "content": ""}
]
load images and prepare for inputs
pil_images = load_pil_images(conversation)
prepare_inputs = vl_chat_processor(
conversations=conversation,
images=pil_images,
force_batchify=True,
system_prompt=""
).to(vl_gpt.device)
run image encoder to get the image embeddings
inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)
run the model to get the response
outputs = vl_gpt.language.generate(
input_ids = prepare_inputs["input_ids"],
inputs_embeds=inputs_embeds,
attention_mask=prepare_inputs.attention_mask,
pad_token_id=tokenizer.eos_token_id,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id,
max_new_tokens=512,
do_sample=False,
use_cache=True
)
answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=False)
print(f"{prepare_inputs['sft_format'][0]}", answer)
’‘’
相较于官方代码就加了一行nput_ids = prepare_inputs["input_ids"],，不加报错。
输出的结果是
请问是什么原因该如何解决
@aastha78 commented on GitHub (Jul 23, 2025):
is it resolved ?