-
I have one 16 GB NVIDIA RTX A4000 GPU. When I run " torchrun --nproc-per-node 1 train.py --cfg-path train_configs/minigpt4_stage2_finetune.yaml " command I got "failed to create process" error. Can an…
-
How can we use RWKV-LMM to implement "infinite" context lengths?
From https://github.com/BlinkDL/RWKV-LM:
> RWKV is an RNN with transformer-level LLM performance. It can be directly trained like…
-
-
**Thank you for sharing such a great project, I am getting an error when trying to deploy this project has reached the final stage：**
(minigpt4) D:\MiniGPT-4>python demo.py --cfg-path eval_configs/mi…
-
When I run python demo.py --cfg-path eval_configs/minigpt4_eval.yaml --gpu-id 0, I get an error when I input text after uploading images to the web page.
Have you ever encountered such a mistake?
-
Encountered `torch.distributed.elastic.multiprocessing.errors.ChildFailedError` during the index_train step, running `bash tools/retro/examples/preprocess_data.sh index-train`
The run command in th…
coree updated
1 month ago
-
这块有训练代码吗？从头开始训练的版本，而不是finetune版本
-
Thanks for the great project, I really like it.
Is it just me or is it normal to have only around 35-45% GPU utilization while it's genereting the reply? All my models are running from m. 2 ssd dr…
-
**Objective**: Create exercises where students have to complete miniGPT code
- [ ] Decide on exercise structure. Normally we have
1. warm-up: some easy example to complete to gain knowledge abo…
-
Hi everyone, I've finished the finetuning stage and how can I launch the model API using this last version I've just finetuned? Best,