bczhou/tiny-llava-v1-hf
Image-Text-to-Text
•
Updated
•
1.46k
•
55
Dataset Preview
Full Screen Viewer
Full Screen
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed because of a cast error
Error code: DatasetGenerationCastError
Exception: DatasetGenerationCastError
Message: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 2 new columns ({'url', 'blip_caption'}) and 1 missing columns ({'conversations'}).
This happened while the json dataset builder was generating data using
hf://datasets/liuhaotian/LLaVA-Pretrain/blip_laion_cc_sbu_558k_meta.json (at revision 70f9d1e5e1a697fe35830875cfc7de1dd590d727)
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback: Traceback (most recent call last):
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 2011, in _prepare_split_single
writer.write_table(table)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 585, in write_table
pa_table = table_cast(pa_table, self._schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2302, in table_cast
return cast_table_to_schema(table, schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2256, in cast_table_to_schema
raise CastError(
datasets.table.CastError: Couldn't cast
url: string
id: string
image: string
blip_caption: string
to
{'id': Value(dtype='string', id=None), 'image': Value(dtype='string', id=None), 'conversations': [{'from': Value(dtype='string', id=None), 'value': Value(dtype='string', id=None)}]}
because column names don't match
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1316, in compute_config_parquet_and_info_response
parquet_operations, partial = stream_convert_to_parquet(
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 909, in stream_convert_to_parquet
builder._prepare_split(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1882, in _prepare_split
for job_id, done, content in self._prepare_split_single(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 2013, in _prepare_split_single
raise DatasetGenerationCastError.from_cast_error(
datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 2 new columns ({'url', 'blip_caption'}) and 1 missing columns ({'conversations'}).
This happened while the json dataset builder was generating data using
hf://datasets/liuhaotian/LLaVA-Pretrain/blip_laion_cc_sbu_558k_meta.json (at revision 70f9d1e5e1a697fe35830875cfc7de1dd590d727)
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
image
string | id
string | conversations
list |
|---|---|---|
00453/004539375.jpg | 004539375 | [
{
"from": "human",
"value": "Render a clear and concise summary of the photo.\n<image>"
},
{
"from": "gpt",
"value": "select luxury furniture 3 - inch gel memory foam mattress topper"
}
] |
00223/002239345.jpg | 002239345 | [
{
"from": "human",
"value": "Write a terse but informative summary of the picture.\n<image>"
},
{
"from": "gpt",
"value": "a grey watch with an army style strap"
}
] |
00594/005947502.jpg | 005947502 | [
{
"from": "human",
"value": "<image>\nWhat is this?"
},
{
"from": "gpt",
"value": "a dragon kite flying in the blue sky stock images"
}
] |
00511/005116462.jpg | 005116462 | [
{
"from": "human",
"value": "<image>\nRender a clear and concise summary of the photo."
},
{
"from": "gpt",
"value": "$ 10 - cute cheap printed mini dress - khaki multicolor striped floral print peasant short sleeve tunic"
}
] |
00201/002017886.jpg | 002017886 | [
{
"from": "human",
"value": "What is in the photo?\n<image>"
},
{
"from": "gpt",
"value": "augmented reality using aruco markers in opencv"
}
] |
00181/001819539.jpg | 001819539 | [
{
"from": "human",
"value": "Describe the image concisely.\n<image>"
},
{
"from": "gpt",
"value": "a pair of childrens boots in the shape of knitted shoes"
}
] |
00283/002838027.jpg | 002838027 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "floral watercolor clip art rose flower border with pink"
}
] |
00040/000406392.jpg | 000406392 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "the divine queen in her elaborate masks canvas print featuring the face and hands of a woman with red hair"
}
] |
00628/006288475.jpg | 006288475 | [
{
"from": "human",
"value": "<image>\nWhat is this?"
},
{
"from": "gpt",
"value": "an aerial view of paris at night from a plane stock photo"
}
] |
00007/000075539.jpg | 000075539 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "the nike air trainer low in desert tan and black"
}
] |
00164/001649122.jpg | 001649122 | [
{
"from": "human",
"value": "<image>\nPresent a compact description of the photo's key features."
},
{
"from": "gpt",
"value": "a illustration of a dj in a crowd with the text so dop"
}
] |
00232/002326944.jpg | 002326944 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "floor plan of cottage type house, 1 bedroom"
}
] |
00009/000093116.jpg | 000093116 | [
{
"from": "human",
"value": "Render a clear and concise summary of the photo.\n<image>"
},
{
"from": "gpt",
"value": "a cat looking back sitting on a rock at the ocean vacation & travel summer beach ocean animal pet animals dog"
}
] |
00095/000951660.jpg | 000951660 | [
{
"from": "human",
"value": "<image>\nDescribe the image concisely."
},
{
"from": "gpt",
"value": "a small toy bin with a raccoon print"
}
] |
00636/006366709.jpg | 006366709 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "business people at conference table, with a text saying why smart managers don't do sales meetings"
}
] |
00020/000205111.jpg | 000205111 | [
{
"from": "human",
"value": "What is this?\n<image>"
},
{
"from": "gpt",
"value": "the peanuts cartoon show, with a girl and a man holding up a sign that says, she's"
}
] |
00306/003062571.jpg | 003062571 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "anker case for the jbl boom 2"
}
] |
00553/005531752.jpg | 005531752 | [
{
"from": "human",
"value": "<image>\nWrite a terse but informative summary of the picture."
},
{
"from": "gpt",
"value": "the front saddle seat pack is attached to a bike's saddle"
}
] |
00538/005389063.jpg | 005389063 | [
{
"from": "human",
"value": "What is this?\n<image>"
},
{
"from": "gpt",
"value": "elisabeth henning"
}
] |
00371/003713357.jpg | 003713357 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "a group of people on an inflatable raft, in a rapid white water river with a wave breaking"
}
] |
00148/001489285.jpg | 001489285 | [
{
"from": "human",
"value": "Summarize the visual content of the image.\n<image>"
},
{
"from": "gpt",
"value": "an orange traffic cone with a red flashing light"
}
] |
00356/003569527.jpg | 003569527 | [
{
"from": "human",
"value": "<image>\nDescribe the image concisely."
},
{
"from": "gpt",
"value": "calculations for pca"
}
] |
00008/000082148.jpg | 000082148 | [
{
"from": "human",
"value": "<image>\nWhat is in the photo?"
},
{
"from": "gpt",
"value": "christmas greeting with wreath and red bauble on white background, scandinavian christmas text"
}
] |
00095/000956213.jpg | 000956213 | [
{
"from": "human",
"value": "Describe the image concisely.\n<image>"
},
{
"from": "gpt",
"value": "nickelodeons new rugger"
}
] |
00649/006498284.jpg | 006498284 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "the coffee maker stickers and stickers pack"
}
] |
00361/003618761.jpg | 003618761 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "arsenal womans 18 / 21 long sleeve training top"
}
] |
00456/004564488.jpg | 004564488 | [
{
"from": "human",
"value": "What is in the photo?\n<image>"
},
{
"from": "gpt",
"value": "a group of british motorcycle gear and helmets"
}
] |
00439/004398009.jpg | 004398009 | [
{
"from": "human",
"value": "Present a compact description of the photo's key features.\n<image>"
},
{
"from": "gpt",
"value": "a burgundy book with a boat floating in the water"
}
] |
00347/003472061.jpg | 003472061 | [
{
"from": "human",
"value": "Summarize the visual content of the image.\n<image>"
},
{
"from": "gpt",
"value": "rochelle lovett and joe manda"
}
] |
00336/003362053.jpg | 003362053 | [
{
"from": "human",
"value": "<image>\nRender a clear and concise summary of the photo."
},
{
"from": "gpt",
"value": "twit, synonym for twit, synonym for twit"
}
] |
00297/002972155.jpg | 002972155 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "the makers faire on a blue and white background with the logo of maker faire on it"
}
] |
00174/001745272.jpg | 001745272 | [
{
"from": "human",
"value": "Give a short and clear explanation of the subsequent image.\n<image>"
},
{
"from": "gpt",
"value": "alpina sunglasses explorer black matt"
}
] |
00044/000448786.jpg | 000448786 | [
{
"from": "human",
"value": "<image>\nGive a short and clear explanation of the subsequent image."
},
{
"from": "gpt",
"value": "two photos one is an orange lamp and the other is a white light"
}
] |
00195/001952409.jpg | 001952409 | [
{
"from": "human",
"value": "<image>\nGive a brief description of the image."
},
{
"from": "gpt",
"value": "the data center features three tablets, a tablet monitor and various diagrams"
}
] |
00041/000412068.jpg | 000412068 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "the nike air zoom elite is a sleek, lightweight shoe that will fit all the needs to pack up with"
}
] |
00193/001938755.jpg | 001938755 | [
{
"from": "human",
"value": "Give a short and clear explanation of the subsequent image.\n<image>"
},
{
"from": "gpt",
"value": "green tackle and ball fundraiser flyer"
}
] |
00264/002648198.jpg | 002648198 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "men's black and red ohio duck river jacket"
}
] |
00317/003172346.jpg | 003172346 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "the aerial view of the marina and resort of benissa, near barcelona, on the coast of the mediterranean"
}
] |
00089/000896428.jpg | 000896428 | [
{
"from": "human",
"value": "<image>\nPresent a compact description of the photo's key features."
},
{
"from": "gpt",
"value": "a phone on a red background, with a white and red text that reads spread positivity"
}
] |
00067/000678978.jpg | 000678978 | [
{
"from": "human",
"value": "Describe the image concisely.\n<image>"
},
{
"from": "gpt",
"value": "ufc ufc announces welterweights to the ring on the next episode of wwe"
}
] |
00145/001455885.jpg | 001455885 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "the chandelier with a glass center and gold finish"
}
] |
00514/005147220.jpg | 005147220 | [
{
"from": "human",
"value": "<image>\nPresent a compact description of the photo's key features."
},
{
"from": "gpt",
"value": "minister vijay kumar reddy addressing to media in visanagar, west bengal | hyderabad tv"
}
] |
00328/003286865.jpg | 003286865 | [
{
"from": "human",
"value": "<image>\nDescribe the image concisely."
},
{
"from": "gpt",
"value": "the midland charity ball flyer"
}
] |
00491/004915801.jpg | 004915801 | [
{
"from": "human",
"value": "What is this?\n<image>"
},
{
"from": "gpt",
"value": "space station and rose tank shirt"
}
] |
00308/003085194.jpg | 003085194 | [
{
"from": "human",
"value": "<image>\nGive a short and clear explanation of the subsequent image."
},
{
"from": "gpt",
"value": "the process of using rfps to identify the operational environment"
}
] |
00408/004088496.jpg | 004088496 | [
{
"from": "human",
"value": "<image>\nRender a clear and concise summary of the photo."
},
{
"from": "gpt",
"value": "a bar graph shows the chromosome level and the age of the kinases of phosphoruso - 308 / mg"
}
] |
00367/003674579.jpg | 003674579 | [
{
"from": "human",
"value": "<image>\nSummarize the visual content of the image."
},
{
"from": "gpt",
"value": "platinum 1 01 princess cut pave diamond engagement rings"
}
] |
00005/000054222.jpg | 000054222 | [
{
"from": "human",
"value": "<image>\nWhat is this?"
},
{
"from": "gpt",
"value": "a drawing of a bonsail with a frame behind it"
}
] |
00106/001066082.jpg | 001066082 | [
{
"from": "human",
"value": "<image>\nGive a short and clear explanation of the subsequent image."
},
{
"from": "gpt",
"value": "the bands against breast cancer logo"
}
] |
00001/000019465.jpg | 000019465 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "the bunk room"
}
] |
00530/005301430.jpg | 005301430 | [
{
"from": "human",
"value": "Present a compact description of the photo's key features.\n<image>"
},
{
"from": "gpt",
"value": "the raven legacy of a master thief"
}
] |
00244/002448962.jpg | 002448962 | [
{
"from": "human",
"value": "<image>\nShare a concise interpretation of the image provided."
},
{
"from": "gpt",
"value": "a porch at rockytop, a 2 bedroom cabin rental located in pigeon country"
}
] |
00109/001095007.jpg | 001095007 | [
{
"from": "human",
"value": "Give a short and clear explanation of the subsequent image.\n<image>"
},
{
"from": "gpt",
"value": "the wrecker by clive cussler and justin scott"
}
] |
00155/001558989.jpg | 001558989 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "new york red bulls bamboo iphone case"
}
] |
00027/000275473.jpg | 000275473 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "the monster girls in the pit at brno"
}
] |
00306/003060719.jpg | 003060719 | [
{
"from": "human",
"value": "Summarize the visual content of the image.\n<image>"
},
{
"from": "gpt",
"value": "the test - footed nerve's steps an evening with frank zappa by michael e schwartz"
}
] |
00535/005353120.jpg | 005353120 | [
{
"from": "human",
"value": "<image>\nWhat is in the photo?"
},
{
"from": "gpt",
"value": "front panel bracket cover for suzuki"
}
] |
00230/002306499.jpg | 002306499 | [
{
"from": "human",
"value": "What is this?\n<image>"
},
{
"from": "gpt",
"value": "vampire nights - the new adventures of vampire nights 1"
}
] |
00115/001154889.jpg | 001154889 | [
{
"from": "human",
"value": "Describe the image concisely.\n<image>"
},
{
"from": "gpt",
"value": "the soprano christmas sweatshirt with a santa claus head on it"
}
] |
00010/000108574.jpg | 000108574 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "rock formations near the dolomite mountains in italy"
}
] |
00005/000051961.jpg | 000051961 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "a model presents a costume in the costume contest"
}
] |
00076/000769514.jpg | 000769514 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "red rock swing band"
}
] |
00500/005002288.jpg | 005002288 | [
{
"from": "human",
"value": "<image>\nDescribe the image concisely."
},
{
"from": "gpt",
"value": "2 piece children turban baby hat fashion pearl flower cotton bow knot headband toddler baby cap cute"
}
] |
00033/000338977.jpg | 000338977 | [
{
"from": "human",
"value": "<image>\nShare a concise interpretation of the image provided."
},
{
"from": "gpt",
"value": "the drum player and drummer of the marching unit march in a parade"
}
] |
00188/001881338.jpg | 001881338 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "a golf flag mounted with the logo of a pga tournament"
}
] |
00047/000477760.jpg | 000477760 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "a portrait of an old woman in a purple dress with tia tia and diamond earrings"
}
] |
00014/000140736.jpg | 000140736 | [
{
"from": "human",
"value": "Provide a brief description of the given image.\n<image>"
},
{
"from": "gpt",
"value": "a gold lamp that is hanging from the ceiling"
}
] |
00046/000466761.jpg | 000466761 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "a clipboard and a pen with the words public health emergency next to it on a white table"
}
] |
00121/001217151.jpg | 001217151 | [
{
"from": "human",
"value": "<image>\nWhat is in the photo?"
},
{
"from": "gpt",
"value": "a single - handle faucet with extended pop - up handles"
}
] |
00003/000033482.jpg | 000033482 | [
{
"from": "human",
"value": "Give a short and clear explanation of the subsequent image.\n<image>"
},
{
"from": "gpt",
"value": "a close up shot of two cups with the nashville skyline in black and white"
}
] |
00155/001553848.jpg | 001553848 | [
{
"from": "human",
"value": "Summarize the visual content of the image.\n<image>"
},
{
"from": "gpt",
"value": "shah qur, his friend, and an indian family in the uae"
}
] |
00376/003761714.jpg | 003761714 | [
{
"from": "human",
"value": "<image>\nWrite a terse but informative summary of the picture."
},
{
"from": "gpt",
"value": "6 plates stainless steel griddle table griddles for electric flat top griddle grill"
}
] |
00287/002879592.jpg | 002879592 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "window catch bronze brass"
}
] |
00199/001999543.jpg | 001999543 | [
{
"from": "human",
"value": "Present a compact description of the photo's key features.\n<image>"
},
{
"from": "gpt",
"value": "a scene from a movie that shows people dancing together in a crowded dance room"
}
] |
00145/001452028.jpg | 001452028 | [
{
"from": "human",
"value": "<image>\nRender a clear and concise summary of the photo."
},
{
"from": "gpt",
"value": "a red and white election 2016 jumbo tote bag"
}
] |
00053/000536940.jpg | 000536940 | [
{
"from": "human",
"value": "<image>\nPresent a compact description of the photo's key features."
},
{
"from": "gpt",
"value": "the marble bathroom features white and black marble walls and floors"
}
] |
00361/003617195.jpg | 003617195 | [
{
"from": "human",
"value": "<image>\nPresent a compact description of the photo's key features."
},
{
"from": "gpt",
"value": "a red tin has the word maxwell house coffee in it"
}
] |
00503/005032770.jpg | 005032770 | [
{
"from": "human",
"value": "<image>\nProvide a brief description of the given image."
},
{
"from": "gpt",
"value": "the new benetem 33"
}
] |
00107/001071511.jpg | 001071511 | [
{
"from": "human",
"value": "<image>\nDescribe the image concisely."
},
{
"from": "gpt",
"value": "a little white baby clothes set with polo neck collar, shorts and shirt"
}
] |
00351/003511400.jpg | 003511400 | [
{
"from": "human",
"value": "Write a terse but informative summary of the picture.\n<image>"
},
{
"from": "gpt",
"value": "anipeit tropical parrot food"
}
] |
00192/001928073.jpg | 001928073 | [
{
"from": "human",
"value": "What is in the photo?\n<image>"
},
{
"from": "gpt",
"value": "a man who loves to play drums mugs"
}
] |
00417/004171642.jpg | 004171642 | [
{
"from": "human",
"value": "Give a short and clear explanation of the subsequent image.\n<image>"
},
{
"from": "gpt",
"value": "bunches of rebars with iron bar"
}
] |
00222/002228340.jpg | 002228340 | [
{
"from": "human",
"value": "<image>\nSummarize the visual content of the image."
},
{
"from": "gpt",
"value": "modeling complex systems volume 23 of the computer vision"
}
] |
00136/001365521.jpg | 001365521 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "a black bmw m140i sports hatch from a dealer's garage"
}
] |
00026/000267756.jpg | 000267756 | [
{
"from": "human",
"value": "<image>\nPresent a compact description of the photo's key features."
},
{
"from": "gpt",
"value": "the main street in malmo, and some people walking around on a sunny day"
}
] |
00421/004211582.jpg | 004211582 | [
{
"from": "human",
"value": "<image>\nWhat is this?"
},
{
"from": "gpt",
"value": "carrs toi n068m2 green black"
}
] |
00650/006509679.jpg | 006509679 | [
{
"from": "human",
"value": "<image>\nSummarize the visual content of the image."
},
{
"from": "gpt",
"value": "6kw invertor battery controller, 3 phase control with power output voltage indicator, 12a"
}
] |
00179/001792187.jpg | 001792187 | [
{
"from": "human",
"value": "<image>\nWhat is this?"
},
{
"from": "gpt",
"value": "a skull and cross bones sticker sits on the floor"
}
] |
00564/005643616.jpg | 005643616 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "an image of a man wearing a multicolored vest tank top"
}
] |
00135/001358562.jpg | 001358562 | [
{
"from": "human",
"value": "Render a clear and concise summary of the photo.\n<image>"
},
{
"from": "gpt",
"value": "purple rain trousers with black and silver reflective details"
}
] |
00284/002846089.jpg | 002846089 | [
{
"from": "human",
"value": "Render a clear and concise summary of the photo.\n<image>"
},
{
"from": "gpt",
"value": "an image of vintage reindeer sweater"
}
] |
00318/003184510.jpg | 003184510 | [
{
"from": "human",
"value": "<image>\nDescribe the image concisely."
},
{
"from": "gpt",
"value": "the quote on positiveness is one of the most difficult things people take different roads"
}
] |
00028/000287377.jpg | 000287377 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "england women's cricketers batsman person plays the ball as she hits out during the cricket international match against"
}
] |
00433/004330598.jpg | 004330598 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "fundamentals of finite element analysis"
}
] |
00017/000176395.jpg | 000176395 | [
{
"from": "human",
"value": "<image>\nRender a clear and concise summary of the photo."
},
{
"from": "gpt",
"value": "cut paper on a piece of craft paper and glue to create the bow"
}
] |
00427/004271632.jpg | 004271632 | [
{
"from": "human",
"value": "Give a brief description of the image.\n<image>"
},
{
"from": "gpt",
"value": "blue cartoon fish photo greeting card"
}
] |
00366/003662504.jpg | 003662504 | [
{
"from": "human",
"value": "<image>\nWrite a terse but informative summary of the picture."
},
{
"from": "gpt",
"value": "the graph shows the trend of carbon dioxide concentrations in earth's atmosphere as compared to the percentage of greenhouse"
}
] |
00317/003174711.jpg | 003174711 | [
{
"from": "human",
"value": "<image>\nWhat is in the photo?"
},
{
"from": "gpt",
"value": "1 month full page seo traffic from seo for the most profitable website"
}
] |
00137/001377789.jpg | 001377789 | [
{
"from": "human",
"value": "Write a terse but informative summary of the picture.\n<image>"
},
{
"from": "gpt",
"value": "the young lady in leopard print pencil skirt"
}
] |
00383/003838999.jpg | 003838999 | [
{
"from": "human",
"value": "Share a concise interpretation of the image provided.\n<image>"
},
{
"from": "gpt",
"value": "assassin's revelations ultimatum edition - pc dvd"
}
] |
End of preview.
LLaVA Visual Instruct Pretrain Dataset Card
Dataset details
Dataset type: LLaVA Visual Instruct Pretrain LCS-558K is a subset of LAION/CC/SBU dataset, filtered with a more balanced concept coverage distribution. Captions are also associated with BLIP synthetic caption for reference. It is constructed for the pretraining stage for feature alignment in visual instruction tuning. We aim to build large multimodal towards GPT-4 vision/language capability.
Dataset date: LLaVA Visual Instruct CC3M Pretrain 595K was created in May 2023.
Dataset structure:
blip_laion_cc_sbu_558k.jsoncontains the multimodal synthesized conversation from the image-caption pairs, by adding randomly selected instructions like: "Describe this image". It is used for pretraining in LLaVA. We use the raw CC-3M caption as the default answer.blip_laion_cc_sbu_558k_meta.jsoncontains the meta data of the image file name, image URL, synthetic BLIP caption.images.zipcontains all raw images of the filtered subset from LAION/CC/SBU. Important notice: Upon the request from the community, as ~15% images of the original LAION/CC/SBU dataset are no longer accessible, we upload images.zip for better reproducing our work in research community. It should not be used for any other purpose. The use of these images must comply with the LAION/CC/SBU license. This may be taken down when requested by the original LAION/CC/SBU dataset owner or owners of the referenced images.
Paper or resources for more information: https://llava-vl.github.io/
License: Must comply with license of CC-3M, BLIP (if you use their synthetic caption).
CC-3M The dataset may be freely used for any purpose, although acknowledgement of Google LLC ("Google") as the data source would be appreciated. The dataset is provided "AS IS" without any warranty, express or implied. Google disclaims all liability for any damages, direct or indirect, resulting from the use of the dataset.
Where to send questions or comments about the model: https://github.com/haotian-liu/LLaVA/issues
Intended use
Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots.
Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
- Downloads last month
- 1,274
