-
国内的大模型对中文的支持比较好,是否计划接入别的大模型?
-
Hello,
How should I run the LoRA finetuning with an own pretrained ViT and pretrained adapter? Do I use `--pretrain_mllm` to give the full pretrained model checkpoint which I get from `pretrain.sh…
-
Hi,
I start the training with run_stage1.sh. One error message comes up when saving the training model at step 3000.
Any suggestions?
Thanks,
--Ruida
tensor(0., device='cuda:1', gra…
ruida updated
7 months ago
-
Thank you very much for sharing this work. I would like to fine-tune the third stage of the LLM using my own instruction dataset on a single 24GB 4090. Is there any way to achieve this, or is it an im…
-
Hi Team,
Thanks for providing such extensive features in one repo!
I would like to know can this activation steering code be applicable on multimodal language model such as instructBLIP, PaliGe…
-
Hello, I would like to ask for assistance in solving a problem I've encountered.
I am currently training a MLLM with DeepSpeed, and I've introduced an additional modality to the existing ones. Howe…
-
Hi
First of all, thanks for your amazing work here.
I’m wondering whether CrewAI would support any MLLM (multimodal large language model)? Since it’s more suitable in my use case. For example, the a…
-
Hi, I'm interested in your great work.
The `./scripts/v1_5/eval/eval_all.sh` is not avalilable now. Could you release the evaluation tools? **Especially the few-shot VQA/Caption.**
And the mmc4 …
-
请问文章中表4在测试Qwen-VL-Chat和MiniGPTv2的定位精度时,是使用的官方发布的预训练模型还是把模型在两个数据集上又分别进行了微调?另外,表4中Visual Grounding精度计算的脚本有开源吗?
-
```
环境
flash-attn @ file:///ssd2/flash_attn-2.6.3%2Bcu118torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl#sha256=b9e51701e981d3c8df0988174a76b8e865027daea2c006e609c39f0fbeba7a2e
torch==2.1.2+cu118
…