chendelong1999 / polite-flamingo Goto Github PK

the error:
Could not create share link. Please check your internet connection or our status page: https://status.gradio.app.
Traceback (most recent call last):
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/gradio/routes.py", line 439, in run_predict
output = await app.get_blocks().process_api(
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/gradio/blocks.py", line 1389, in process_api
result = await self.call_function(
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/gradio/blocks.py", line 1094, in call_function
prediction = await anyio.to_thread.run_sync(
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread
return await future
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 851, in run
result = context.run(func, *args)
File "/root/miniconda3/envs/openflamingo/lib/python3.9/site-packages/gradio/utils.py", line 704, in wrapper
response = f(*args, **kwargs)
File "/root/paddlejob/workspace/env_run/code/polite-flamingo/gradio_demo.py", line 185, in bot
inference_results = inferencer(
File "/root/paddlejob/workspace/env_run/code/polite-flamingo/gradio_demo.py", line 47, in call
return clever_flamingo_api(prompt, imgpaths)
File "/root/paddlejob/workspace/env_run/code/polite-flamingo/gradio_demo.py", line 45, in clever_flamingo_api
return js['result']['response']
version:
gradio: 3.37.0

https://github.com/ChenDelong1999/polite_flamingo/blob/bf8ef5e103bf7c86a2a4a2b5eae3f89c8580cfb6/polite_flamingo/src/factory.py#L93-L101

From my understanding of above code, is the PF's training part a LoRA LLM?

Thanks for your time in advance!

This work is wonderful.
However, when I downloading the datasest, I found that the released resized_images.zip in huggingface are not all the images corresponding to PF-1M.json. I wonder whether you plan to open all the images contained in PF-1M.json?
Thanks~

Dear authors,

Great work, and I really enjoyed reading the paper -- I appreciate the efforts undertaken to ensure high quality data for instruction tuning LMMs. Further, the results in Table 2 (multi-image reasoning) are impressive -- to the best of my knowledge, not many other foundational LMMs can perform well on multi-image reasoning benchmarks. I would like to play around with the models (CleverFlamingo) especially for these tasks.
Do you have an estimated timeline for when you could release the code and CleverFlamingo checkpoints? Further, if it would be possible I would request you to release the evaluation scripts used for the numbers in Table 2!

Looking forward to the release!

Hello authors. Thanks for your effort in dataset contribution, but I feel confused to align the image in PF-1M to the open-source dataset [PointingQA]. For example,
<img_path>/pointingga-main/Datasets/LookTwiceQA/images_with_points_train/train_42636.jpg<img_path>
how to find this image in [PointingQA] or [Visual Genome]?