MiniGPT-4

MiniGPT-4 copied to clipboard

yuchenlichuck

请问如果一台主机上使用两块RTX 4090显卡，使用Pytorch加载Vicuna-13B模型，是否能将内存分配在两块显卡上？

4

目前4090显卡只有24GB内存，如果尝试加载Vicuna-13B模型可能会出现内存不足，能否在一块主板上插上两块4090显卡，使得两块显卡的内存合并使用？

ruoyiran

13B only 45M？

hktalent

I upload a image to gradio.live output error info: Traceback (most recent call last): File "/data1/miniconda3/envs/minigpt4/lib/python3.9/site-packages/gradio/routes.py", line 393, in run_predict output = await app.get_blocks().process_api( File "/data1/miniconda3/envs/minigpt4/lib/python3.9/site-packages/gradio/blocks.py", line 1108, in process_api...

wuhongsheng

RuntimeError: The size of tensor a (32000) must match the size of tensor b (32001) at non-singleton dimension 0

11

RuntimeError: The size of tensor a (32000) must match the size of tensor b (32001) at non-singleton dimension 0 after I execute this command：python -m fastchat.model.apply_delta --base llama-7b-hf/ --target vicuna-7b/...

Coca-Cola1999

BadarSaghir

A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set `padding_side='left'` when initializing the tokenizer.

12

I use ``` python demo.py ``` it runs well. however when I asked the model in the webui, it shows in the terminal: A decoder-only architecture is being used, but...

Ethan-Chen-plus

I want to run it in MacbookPro M1,but have a ValueError!

3

[I want to run it in MacbookPro M1,but have a ValueError: Tokenizer class LLaMATokenizer does not exist or is not currently imported. After executing this command : python -m fastchat.model.apply_delta...

Coca-Cola1999

After a number of messages (depends on their token volume), the bot starts to talk gibberish like a mental asylum patient (beam search and temperature are at their default value:...

OcelotTheOcelot

error: the following arguments are required: --cfg-path

2

how to do it? 

kdoat