tsb0601/MMVP

Issues

• Why is CLIP model created during loading od DINO Encoder?

  #24 opened 17 days ago by HashmatShadab
  0

• dino v2 num paches set to 256

  #19 opened 3 months ago by yanbai1993
  3

• How to reproduce the result of Figure 6?

  #3 opened 8 months ago by HenryHZY
  8

• Training Time details

  #22 opened 3 months ago by HashmatShadab
  1

• instruction fine-tuning failed.

  #6 opened 7 months ago by shengyuwoo
  3

• Discrepancy between the code and Table 1 in the paper

  #5 opened 7 months ago by MajorDavidZhang
  3

• LLaVA-1.5 stage2 Traing batchsize

  #13 opened 6 months ago by Z-MU-Z
  1

• Implementation Details of Additive-MoF

  #23 opened 2 months ago by Leeinsu1
  0

• how to reproduce the siglip's performance on MMVP-VLM Benchmark?

  #20 opened 2 months ago by Rubics-Xuan
  0

• evaluate on the MMVP

  #21 opened 3 months ago by jiaxi0030
  0

• CLIP-blind pairs

  #10 opened 6 months ago by mahtabbigverdi
  2

• COMM (which has already been on Arxiv on 2023.10 https://arxiv.org/pdf/2310.08825.pdf) already proposed to merge the features of CLIP and DINOv2 to realize MLLM, maybe this paper should cite this reference.

  #18 opened 5 months ago by YuchenLiu98
  0

• Is the result of MMVP-VLM sensitive to the presentation of the statement?

  #17 opened 5 months ago by XiaohuJoshua
  0

• pretrain_dino_mm_mlp_adapter

  #16 opened 5 months ago by demo1shining
  0

• Unable to load the provided pretrained

  #15 opened 5 months ago by sunfanyunn
  0

• Correction Needed for Incorrect Answers in MMVP Benchmark Questions 279 and 280

  #14 opened 5 months ago by MajorDavidZhang
  0

• The accuracy of LLaVA-1.5-7b with CLIP encoder is 60.0 on MMVP

  #8 opened 7 months ago by Richar-Du
  3

• Index Overflow in position_ids when evaluate on mmvp

  #12 opened 6 months ago by Z-MU-Z
  1

• GPT4-V Prompt Used in Evaluation

  #11 opened 6 months ago by Nyandwi
  0

• leaked api key

  #7 opened 7 months ago by lucasrodes
  1

• Answer sheet of LLMs on MMVP?

  #9 opened 7 months ago by minhlong94
  1

• How to evaluate the DFN model?

  #4 opened 7 months ago by DesertsP
  1

• 下载模型的是否需要放在具有特殊名字的文件夹里（evaluate时）

  #2 opened 7 months ago by Pro-flynn
  5

• bug in evaluate scripts?

  #1 opened 8 months ago by LightDXY
  1