Aritra Dutta

dutta18's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in lmms-lab-encoder/DocVQA 4 months ago

DataFilesNotFoundError: No (supported) data files found in lmms-lab/DocVQA

#5 opened 4 months ago by

dutta18

New activity in google/gemma-3-4b-it 5 months ago

Finetuning Code Link In Native PyTorch

1

#87 opened 5 months ago by

dutta18

New activity in mistralai/Ministral-3-3B-Instruct-2512 5 months ago

How to use local image in the chat template?

#15 opened 5 months ago by

dutta18

New activity in lmms-lab/LongVA-7B 6 months ago

TypeError: unsupported operand type(s) for //: 'int' and 'NoneType' while calling the processor

#1 opened 6 months ago by

dutta18

New activity in mPLUG/mPLUG-Owl3-7B-240728 6 months ago

KeyError: None for when the model.generate() method is executed in mPlugOwl3

1

#8 opened 6 months ago by

dutta18

New activity in aws-prototyping/long-llava-qwen2-7b 6 months ago

Model's processor have small bug in the integer division.

#2 opened 6 months ago by

dutta18

How to use this model for inference on videos?

1

#1 opened 6 months ago by

dutta18

New activity in HuggingFaceTB/SmolVLM-256M-Instruct 8 months ago

can not believe, but seems 256M is slower then internvl-1B ?

1

#25 opened 9 months ago by

josefph

New activity in microsoft/Phi-3.5-vision-instruct about 1 year ago

RuntimeError: FlashAttention only support fp16 and bf16 data type with Flash attention2

1

#33 opened over 1 year ago by

liougehooa

New activity in openbmb/MiniCPM-V-2 over 1 year ago

Does this model support batch inference?

2

#8 opened over 2 years ago by

vahyd

New activity in microsoft/Phi-3.5-vision-instruct over 1 year ago

Finetuning script for Phi3.5-Vision

❤️ 3

4

#24 opened almost 2 years ago by

2U1

New activity in Qwen/Qwen2-VL-2B-Instruct over 1 year ago

How to do batch inference on Qwen2-VL-2B-Instruct?

2

#20 opened over 1 year ago by

dutta18

New activity in microsoft/Florence-2-large almost 2 years ago

How to add additional prompt in florence in addition to the existing tokens like "<OD>", " <DETAILED_CAPTION>" and etc ?

3

#67 opened almost 2 years ago by

dutta18

Assert config.vision_config.model_type == 'davit', 'only DaViT is supported for now'

4

#44 opened about 2 years ago by

Glider95

How to add additional prompt in florence in addition to the existing tokens like "<OD>", " <DETAILED_CAPTION>" and etc ?

3

#67 opened almost 2 years ago by

dutta18