Issues

• 邀请 llama-adapter 加入 GithubStarMate，让更多人发现你的作品

  OpenGVLab/LLaMA-Adapter#372 · Filter by author camel3811 opened on Sep 30, 2026

• Experiments and Compatibility with LLaMA 3

  OpenGVLab/LLaMA-Adapter#160 · Filter by author sym0 opened on Jan 23, 2026

• Is there a way to apply LLaMA-Adapter-v1 to latest versions of LLaMA(LLaMA 2 or LLaMA 3)?

  OpenGVLab/LLaMA-Adapter#159 · Filter by author KaiSianGG opened on Apr 17, 2025

• Are you going to support vllm for inference?

  OpenGVLab/LLaMA-Adapter#158 · Filter by author denadai2 opened on Feb 14, 2025

• reproduce result on ScienceQA

  OpenGVLab/LLaMA-Adapter#157 · Filter by author Saisai-Xia opened on Dec 26, 2024

• Reproduce results on Open LLM benchmark

  OpenGVLab/LLaMA-Adapter#155 · Filter by author nghiemkythu opened on Dec 24, 2024

• created a model on colab but cannot load for inference

  OpenGVLab/LLaMA-Adapter#153 · Filter by author sedici16 opened on Jul 26, 2024

• RuntimeError: [enforce fail at CPUAllocator.cpp:68] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 90177536 bytes. Error code 12 (Cannot allocate memor y)

  OpenGVLab/LLaMA-Adapter#152 · Filter by author armitamani opened on Apr 11, 2024

• RuntimeError: CUDA out of memory

  OpenGVLab/LLaMA-Adapter#151 · Filter by author 2016110071 opened on Apr 11, 2024

• what is the dataset during pretraining llama_adapter_v2_multimodal7b?

  OpenGVLab/LLaMA-Adapter#150 · Filter by author yabuke opened on Apr 8, 2024

• The meaning of C_loss and M_loss

  OpenGVLab/LLaMA-Adapter#149 · Filter by author 9p15p opened on Mar 22, 2024
  1

• imagebind_LLM中的get_chinese_llama.py文件丢失，可以补充一下吗？

  OpenGVLab/LLaMA-Adapter#146 · Filter by author hyyuan123 opened on Feb 20, 2024
  1

• Simple question about llama adapter v1 transformer forward function

  OpenGVLab/LLaMA-Adapter#145 · Filter by author yestaehyung opened on Feb 13, 2024
  1

• Loss is nan, stopping training, while trying to reproduce alpaca_finetuning_v1 results.

  OpenGVLab/LLaMA-Adapter#144 · Filter by author NavaneethNidadavolu opened on Feb 8, 2024
  2

• Getting error "AF_UNIX path too long"

  OpenGVLab/LLaMA-Adapter#143 · Filter by author GussailRaat opened on Feb 3, 2024

• Don't find save path"ADAPTER_PATH"

  OpenGVLab/LLaMA-Adapter#142 · Filter by author cyZhang00 opened on Jan 24, 2024
  1

• AssertionError: Loading a checkpoint for MP=0 but world size is 1

  OpenGVLab/LLaMA-Adapter#140 · Filter by author IsraelAbebe opened on Dec 31, 2023
  2

• how to set llama adapter max_seq_len = 4096

  OpenGVLab/LLaMA-Adapter#138 · Filter by author foreverpiano opened on Dec 11, 2023

• Inquiry on Loading LLaMa-2 Model Parameters

  OpenGVLab/LLaMA-Adapter#137 · Filter by author FairyFali opened on Dec 3, 2023
  1

• I don't know which data to use to reproduce the model llama-adapter-multimodal-v2.

  OpenGVLab/LLaMA-Adapter#135 · Filter by author yeonju7kim opened on Nov 25, 2023

• question about Pretrained LLAMA applicable to Llama_adapter model. thanks

  OpenGVLab/LLaMA-Adapter#134 · Filter by author jzssz opened on Nov 24, 2023
  1

• Unable to produce the result between LLaMA-Adapter V1 and Alpaca

  OpenGVLab/LLaMA-Adapter#133 · Filter by author vicissitude1999 opened on Nov 23, 2023
  1

• Could you please provide these weight with me?

  OpenGVLab/LLaMA-Adapter#132 · Filter by author fengmingfeng opened on Nov 21, 2023
  2

• The true weight file not find?

  OpenGVLab/LLaMA-Adapter#131 · Filter by author fengmingfeng opened on Nov 20, 2023
  4

• How to fine-tune the llama-adapter-v2 for llama-2 7b models.

  OpenGVLab/LLaMA-Adapter#129 · Filter by author Harsh-raj opened on Nov 11, 2023
  1