MiniGPT-4

MiniGPT-4 copied to clipboard

无法结合原始重量和增重

18

在执行 python -m fastchat.model.apply_delta --base llama-13b/ --target save/working/vicuna/weight/ --delta vicuna-13b-delta-v0/ 命令的时候 顺利读取了原始文件和增重文件 然后报错了，有大神能看看是什么导致了，检查了以下，库应该是完整安装了的

kikotrtr1

Could I have the stage 1 checkpoint model?

3

Good morning, could I have the stage 1 checkpoint model? As I would like to fine tune the model on stage 2 with my own dataset, thanks for your help!

chikiuso

Benchmark of miniGPT-4 vs. SceneX vs Midjourney `/describe` for Understanding Complex Scenes

3

did a benchmark  full article on experiment https://jina.ai/news/scenexplain-vs-minigpt4-a-comprehensive-benchmark-of-top-5-image-captioning-algorithms-for-understanding-complex-scenes/

hanxiao

Mistake in the preparation of vicuna weights (error when loading delta weights)

7

I run the script to get the vicuna weights and get the following error: python -m fastchat.model.apply_delta --base I:\chatgpt\minigpt4\MiniGPT-4\llama-13b-hf --target I:\chatgpt\minigpt4\MiniGPT-4\model --delta I:\chatgpt\minigpt4\MiniGPT-4\vicuna-13b-delta-v0 

huangzhongzhong

corrected typos in README.md

2

N4RMA

So sometimes this model may describe images with imagination?

2


LSH9832

Batch process feature - very need!

2

Plz add batch for process directory of jpg files! Thanks.

goblin776655

Unable to combine Vicuna’s delta weight and original weight

3

Has anyone else had the same problem as me?  I followed PrepareVicuna.md and download llama-13b-hf by `git clone https://huggingface.co/decapoda-research/llama-13b-hf`. But in the last step, the problem happened. Could this...

hayleeXinyi

有人成功了吗？

27

我试图用我的3060（12G）跑，内存不够，需要什么配置的卡才能成功呀，多卡行不行 我在huggingface上建立了一个空间，MiniGPT-4的docker部署，有没有成功的大佬来指点一下 https://huggingface.co/spaces/zylj/MiniGPT-4 

Vector-Cross

HuggingFace -> Hugging Face

eltociear