-
Train multi-modal, with limited resource
-
### Bug Report
Right now, GPT4All only utilizes 1 GPU so for machines with multiple GPU's, it blocks them from having access to higher parameter count models to use.
### Steps to Reproduce
…
-
How best to take into account other models in the ScenarioMIP
- [ ] account for different resolutions / grid placement
-
Originally proposed as, and closes #865
The LAB paper implements training in the following way:
```[Knowledge Training --> MMLU best checkpoint picking --> Skills Training --> MT-Bench best chec…
-
### Is your feature request related to a problem? Please describe.
In order to better support the direction of lula, it may be beneficial to work on a way to handle validation for yaml files with mul…
-
If I want to extend the existing functionality for Whisper recognizer and pass a language at runtime, what would be a recommended approach? I looked at the decode() API, there are a lot of changes re…
-
### Prerequisites
- [X] I am running the latest code. Mention the version if possible as well.
- [X] I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md)…
-
### 🚀 The feature, motivation and pitch
Currently, in GPUExecutorAsync's[ execute_model_async](https://github.com/vllm-project/vllm/blob/main/vllm/executor/gpu_executor.py#L117-L118), it use make_asy…
-
Hi, thank you for your excellent repo!
Do you have any plan to develop a multi-language model?
-
Hi,
I have read your paper. It's very interesting. I am working in the same research area. Can you please provide your pretrained model on Multi Sports Dataset? It would really help my research.
T…