OpenGVLab
/

InternVL3_5-8B

Image-Text-to-Text

feature-extraction

Model card Files Files and versions

Resources

View closed (1)

InternVL config to_dict() includes non-JSON-serializable fields (e.g., torch.dtype), causing PretrainedConfig.repr to crash in vLLM Ray mode

#11 opened about 10 hours ago by

Token Count Calculation in SFT Data Distribution Curation

#10 opened about 2 months ago by

pull

#9 opened 2 months ago by

Resolution

#8 opened 3 months ago by

Add Hugging Face Space link to metadata for InternVL3_5-8B

#7 opened 4 months ago by

Video prefix incorrect : Frame{i} vs Frame-{i}

#6 opened 4 months ago by

How to solve `AttributeError: Qwen2TokenizerFast has no attribute start_image_token`

#5 opened 4 months ago by

CublasLt error when running in 8bit

#4 opened 4 months ago by

what is the recommended method to start up the vllm server engine for inferencing for InternVL3_5-8B, getting 2 qps?

#3 opened 4 months ago by

Fine tuning?

#2 opened 5 months ago by