-
hi，can you release 7B ckpt in first stage？thx
-
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 2.00 MiB (GPU 0; 31.88 GiB total capacity; 30.82 GiB already allocated; 1.94 MiB free; 31.50 GiB reserved in total by PyTorch) If res…
-
-
讲一下cpu的推理思路，大概需要60gb内存和6g显存
首先删掉对于gpuid的要求，或者干脆不传
parser.add_argument("--gpu-id", help="specify the gpu to load the model.")
所有用到--gpu-id的地方换成device='cpu'
model = model_cls.from_config(model_con…
-
或者bt种子什么的，小弟先谢谢了。。
哎，这个翻墙真是麻烦啊。。。
-
RuntimeError: Internal: src/sentencepiece_processor.cc(890) [model_proto->ParseFromArray(serialized.data(), serialized.size())]
self.llama_tokenizer = LlamaTokenizer.from_pretrained
-
artgpt has a big boost to photo descriptions in art,I have seen that you create a small (3500 pairs in total) yet high-quality dataset,can you public this dataset?thx
-
Hi, thanks for sharing this great project! I am transferring the minigpt-4 to a downstream dataset. The training of downstream dataset is fine, but for the validation/test splits I encountered some pr…
-
## Overview
- We need your help to deploy a large language model on NVIDIA Jetson devices and allow people can use words to control the connections/interfaces on the board.
- This is the preparation…
-
Thanks for your excellent work! In my case there is no network connection and gradio is unusable. Could you please share a demo script without gradio? It will be helpful for me.