yxuansu/PandaGPT

Issues

• Can I use Vicuna weightsv1.5 (llama2) instead of v0 (llama)?

  #26 opened 4 months ago by SkiddieAhn
  0

• web demo 报错

  #25 opened 6 months ago by Joe2loft
  2

• 输入图片，生成乱码是什么原因？

  #10 opened a year ago by mlhui
  3

• error

  #21 opened a year ago by south20
  1

• Some weights of LlamaForCausalLM were not initialized from the model checkpoint at ../pretrained_ckpt/vicuna_ckpt/7b_v0/ and are newly initialized

  #23 opened a year ago by Junnian
  1

• Some errors appeared in your demo.

  #24 opened 10 months ago by Leon1207
  0

• train_batch_size / re-train on Vicuna7B_v1.5

  #19 opened 10 months ago by apntel
  0

• demo里怎么没有看到IMU数据的输入？模型不支持IMU数据吗？

  #22 opened a year ago by Junnian
  0

• Any plans to release this for languageBind model?

  #20 opened a year ago by abhimanyu891998
  0

• The issue of the input of caption

  #18 opened a year ago by liuxuannan
  0

• AttributeError: 'OpenLLAMAPEFTModel' object has no attribute 'generate_one_sample

  #17 opened a year ago by shuxiaobo
  0

• Saving Error

  #16 opened a year ago by shuxiaobo
  1

• Deepspeed error: The server socket has failed to listen on any local network address. The server socket has failed to bind to [::]:28457 (errno: 98 - Address already in use).

  #15 opened a year ago by Dongzhikang
  1

• Does it support multi image input？

  #14 opened a year ago by hangzeli08
  1

• 请问我想在你们的基础上继续训练stage，应该怎么改openllama_peft_stage_1.json这个文件？

  #13 opened a year ago by hangzeli08
  1

• [Question] PandaGPT with llama.cpp

  #12 opened a year ago by ningshanwutuobang
  0

• RuntimeError: PytorchStreamReader failed locating file data.pkl: file not found

  #11 opened a year ago by CEDIDataVault
  1

• A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set `padding_side='left'` when initializing the tokenizer.

  #9 opened a year ago by mlhui
  1

• Video encoding for inference

  #4 opened a year ago by bitnom
  2

• 支持文档解读么？

  #5 opened a year ago by ucas010
  4

• On Lora Hyperparameter

  #7 opened a year ago by DaehanKim
  2

• warning: the following paths have collided (e.g. case-sensitive paths on a case-insensitive filesystem)

  #8 opened a year ago by jadedgnome
  0

• About model size

  #6 opened a year ago by David-Zeng-Zijian
  1

• Hello, I am working with a group of people on a project involve pandagpt

  #3 opened a year ago by Alignment-Lab-AI
  0

• Inquiry about using LoRA

  #2 opened a year ago by pipilurj
  2

• Training Stage

  #1 opened a year ago by gordonhu608
  1