Repository Issue Activity (beta)

#84 Errors in comments of Embodied/eaglevl/train/augmentation.py

#40 Eagle-Video-110K Release

#90 [Question] how to train DPO dataset in stage 1 and stage 2?

#89 Tensor-RT Support for Locate-Anything

#51 Release LocateAnything-Data on Hugging Face

#88 Verify evals on Papers with Code

#87 flex_flash_attn only supports sm90 on RTX 5090 (sm120)

#86 Question about future support for visual prompts (bounding box as input) in LocateAnything

#65 out of memory

#85 Continual SFT for LocateAnything: AssertionError and ValueError

#74 how to process negative image data for object detection or grounding task?

#82 Detecting and Locating Objects by Following Labels

#83 Questions about some specific scenarios

#81 Fine-tuning LocateAnything with Lora

#80 Floor Plan Detection

#79 [Blackwell Report] Compatibility with DGX Spark (GB10, sm_121) — inference support?

#78 feature request: batched inference for predict / generate

#71 NotImplementedError: self._attn_implementation='flash_attention_2'

#76 Default top_k=0 crashes single-image LocateAnythingWorker inference

#77 Regarding inference parameter settings

#68 OutOfMemoryError in single L40 GPU

#75 fune train

#72 LM Studio

#73 LM Studio

#70 locate anything backbone generalization