OpenGVLab / LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

OpenGVLab/LLaMA-Adapter Issues

imagebind_LLM中的get_chinese_llama.py文件丢失，可以补充一下吗？
Updated 10 days ago
Can't find forward_only function
Updated 22 days ago5
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)
Updated a month ago
RuntimeError: CUDA out of memory
Updated a month ago
Loss is nan, stopping training, while trying to reproduce alpaca_finetuning_v1 results.
Updated a month ago1
what is the dataset during pretraining llama_adapter_v2_multimodal7b?
Updated a month ago
请问pretrain中的训练集有可以分享的地址吗，从官方下载太慢了
Updated a month ago1
Is the llama adapter v2 code not available yet?
Updated a month ago2
The meaning of C_loss and M_loss
Updated 2 months ago1
Assertation Error start_pos- AdapterV2 Multimodal
Closed 2 months ago
Getting weird output for multimodal 7B adapter
Closed 2 months ago3
Does the LLama pre-trained model you used support Chinese? 您提及的使用的llama的预训练模型（在您给出的以下链接）支持中文吗？
Updated 3 months ago2
Simple question about llama adapter v1 transformer forward function
Updated 3 months ago
Getting error "AF_UNIX path too long"
Updated 3 months ago
Don't find save path"ADAPTER_PATH"
Updated 4 months ago1
AssertionError: Loading a checkpoint for MP=0 but world size is 1
Updated 4 months ago2
[LLaMA Adapter V2] Evaluation on multiple choice questions.
Closed 5 months ago1
Inquiry on Loading LLaMa-2 Model Parameters
Updated 5 months ago1
how to set llama adapter max_seq_len = 4096
Updated 5 months ago
Meaningless results when running demo.py
Updated 5 months ago4
With my custom dataset, output is nan.
Closed 6 months ago1
The true weight file not find?
Updated 5 months ago4
Could you please provide these weight with me?
Updated 5 months ago2
Unable to produce the result between LLaMA-Adapter V1 and Alpaca
Updated 6 months ago1
Does storage space in the paper mean the capacity of checkpoint file?
Closed 6 months ago2
question about Pretrained LLAMA applicable to Llama_adapter model. thanks
Updated 6 months ago1
I don't know which data to use to reproduce the model llama-adapter-multimodal-v2.
Updated 6 months ago
I have problem with downloading 7B_chinese in imagebind_LLM.
Updated 6 months ago1
How to fine-tune the llama-adapter-v2 for llama-2 7b models.
Updated 6 months ago1
Not able to reproduce results of llama-adapter-v2
Updated 6 months ago1
SHA256 checksum does not not match for LORA-BIAS-7B-v21
Updated 6 months ago1
Why do you use only the first conversation when you train llava task?
Closed 6 months ago5
How many training epochs to replicate coco result using llama v1
Updated 7 months ago1
Can I attach multi adapter?
Updated 7 months ago3
Is there any acceleration methods during trianing?
Updated 7 months ago1
question about model.py in alpaca_finetuning_v1
Closed 8 months ago
URL error
Updated 8 months ago1
why not use self.clip.transformer when training?
Updated 8 months ago1
Llama-adapter-v2 compatibility with llama2
Updated 8 months ago9
The Link to Pre-trained Model of LLaMA-Adapter-V2 Multi-modal Is Expired
Closed 8 months ago1
Simple question about generate function when inferencing
Closed 8 months ago2
Can the llama_adapter_v2_multimodal7b model run on multiple GPUs?
Updated 8 months ago1
Blank output for llama_adapter_v2_multimodal7b demo
Closed 8 months ago6
module 'llama' has no attribute 'load'
Updated 8 months ago1
AttributeError: module 'clip' has no attribute 'load'
Closed 9 months ago2
why read url images using cv2.imread()?
Updated 9 months ago3
what is the training target and how to calculate the loss in pretraining and finetuning.
Updated 9 months ago1
Self and mat2 must have the same type
Closed 9 months ago1
RuntimeError: The size of tensor a (730) must match the size of tensor b (257) at non-singleton dimension 1
Updated 9 months ago1
error when pretrin the llama-adapterv2-multimodal
Updated 9 months ago2