Ask-Anything

Ask-Anything copied to clipboard

Cannot access to MVBench

1

 Hi, I cannot visit this page:https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat/video_chat2/MVBench.md Thank you for your support and fantastic work!

Leo-Yuyang

Fix LLaMA2 dead link in README.md

1

The old deepcoda link is dead. The official LLaMA2 HF repo is working: https://huggingface.co/meta-llama/Llama-2-13b-hf/tree/main?clone=true

zhanwenchen

AttributeError: 'LlamaForCausalLM' object has no attribute 'logger'

1

error log Traceback (most recent call last): File "/opt/conda/lib/python3.10/site-packages/peft/peft_model.py", line 288, in __getattr__ return super().__getattr__(name) # defer to nn.Module's logic File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1265, in __getattr__ raise AttributeError("'{}' object has...

chuch1983

Checkpoint fails to match the models

1

Hi, I followed the instruction to download all the weights for doing inference with VideoChat. However, I see the following errors: `Load VideoChat from: /home/ytang/workspace/modules/Ask-Anything/video_chat/model/videochat_7b.pth _IncompatibleKeys(missing_keys=['query_tokens', 'visual_encoder.cls_token', 'visual_encoder.pos_embed', 'visual_encoder.patch_embed.proj.weight', 'visual_encoder.patch_embed.proj.bias',...

YingtianDt

stage 3 cpkt for zero-shot NextQA

1

Hello, could you please release the stage 3 checkpoint for zero-shot NextQA, which in the paper is obtained by performing stage 3 instruction tuning without the NextQA dataset?

yuanrr

Can I train with freeze_mhra=True? (in config_7b_stage1.py) In other words can I totally freeze the visual encoder and train a model that works? Thanks

adeobootpin

这个样例中的视频 ;-(

1

无敌了。。。 ：-（，无处不在，笑哭

wuhaolxp

Video MiniGPT4

8

Firstly, thanks for your interesting work. For minigpt4, can it be realized directly using video embedding? Just like, ```python query_tokens = self.query_tokens.expand(image_embeds.shape[0], -1, -1) query_output = self.Qformer.bert( query_embeds=query_tokens, encoder_hidden_states=image_embeds, encoder_attention_mask=image_atts,...

pixeli99

[Feature Request] Live Stream Video with Adjustable Prompt in Realtime 🔥

1

Hi there! First of all, let me say, this is cutting edge stuff, amazing Wanted to ask, how can we do this on live video? And what should the expected...

fire17

[PERFORMANCE_REPORT]+[OPTIMIZATION]/[SUGGESTION]

2

Sadly can not get stablelm to work on 1070 w 8G vram and 36 gb vram. Sad to compile all on win to see it crash but hey. Here's a...

spacewalkingninja