SHI-Labs / CuMo

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Apache License 2.0
132 stars 11 forks source link

NameError: name 'LlavaMixtralForCausalLM' is not defined #1

Closed leoozy closed 4 months ago

leoozy commented 4 months ago

Traceback (most recent call last): File "/data/users/zhangjunlei/anaconda3/envs/webagent/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/data/users/zhangjunlei/anaconda3/envs/webagent/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/data/users/zhangjunlei/download/install/CuMo/cumo/serve/cli.py", line 112, in main(args) File "/data/users/zhangjunlei/download/install/CuMo/cumo/serve/cli.py", line 32, in main tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, args.load_8bit, args.load_4bit, device=args.device) File "/data/users/zhangjunlei/download/install/CuMo/cumo/model/builder.py", line 118, in load_pretrained_model model = LlavaMixtralForCausalLM.from_pretrained( NameError: name 'LlavaMixtralForCausalLM' is not defined

makemecker commented 4 months ago

Hello!

I am facing the same error when running the command to pre-train the MLP connector (getting_started.md):

bash scripts/cumo/mistral_7b/pretrain_mistral_7b.sh

I tried adding the line to the script scripts/cumo/mistral_7b/pretrain_mistral_7b.sh:

from llava.model.language_model.llava_mistral import LlavaMistralForCausalLM

However, this led to an error:

ImportError: cannot import name 'LlavaLlamaForCausalLM' from 'llava.model' (/home/tyugunov/modules/llava/llava/model/__init__.py)

@leoozy, could you please share how you resolved this issue?

Thank you!