InternVL

InternVL copied to clipboard

InternVL-Chat-V1-5 Batch Inference

4

Hello - I want to perform batch inference using OpenGVLab/InternVL-Chat-V1-5. - Could you give me some tips or suggest examples to refer to? Thank you.

choibigo

Scripts to continue finetuning InternVL-chat-v1-5 on custom data

3

Hi @czczup Could you please provide/update scripts to further [finetune InternVL-Chat v1.5 on custom data](https://github.com/OpenGVLab/InternVL/blob/main/internvl_chat/CONTINUED_FINETUNE.md). Thank you.

swz30

InternVL CLIP Compatibility

5

Hello, hope the authors are doing well. I am wondering if there is a way to get an InternVL model to function as a standard CLIP Vision tower. I am...

puffy310

OCR微调模版

2

请问OCR任务的V1.2-plus的微调，prompt的模版格式是什么？尤其是多行文字的情况

Pro-flynn

OpenGVLab/InternViT-6B-448px-V1-5如何多卡运行

4

单卡最大16g，示例代码跑不起来，使用了CUDA_VISIBLE_DEVICES=1,0或export CUDA_VISIBLE_DEVICES=0,1都还是默认单卡运行，请问16+12够运行吗，如何多卡运行呢

GITRMG

请教一下InternVL-Chat-V1.5如何进行lora微调呢

6

zhangfan-algo

Do you plan on releasing the dataset used to train internVL 1.5 ?

1

Hello, As stated in the huggingface page of InternVL 1.5, a High-Quality Bilingual Dataset was used to train this model. Do you plan to release this dataset in the future...

Mohamed-Dhouib

internvl-chatv1.2-plus 多张图片如何传给模型

5

shanren521

4-bit version

5

Is there a plan to release a normalized 4-bit version?

lihan

ValueError: Tokenizer class InternLM2Tokenizer does not exist or is not currently imported.

3

# error information ``` Traceback (most recent call last): File "/home/sxjiang/project/InternVL/test_chat.py", line 13, in tokenizer = AutoTokenizer.from_pretrained(path) File "/home/sxjiang/miniconda3/envs/internvl/lib/python3.9/site-packages/transformers/models/auto/tokenization_auto.py", line 784, in from_pretrained raise ValueError( ValueError: Tokenizer class InternLM2Tokenizer does...

threegold116