David Andrews

I was trying out the second example you showed in the README on my ipad but the dpad is not even a dpad, it is just a black dot. Also...

Pretrained model?

5

Can a pretrained model be included so that we don't have to train it ourselves?

I'm using the quantization script in examples/quantization and I'm running into an issue where I'm quantizing Mistral 7B to int4_awq and since Mistral 7B is bfloat16, I need to use...

Llama3 ChatFormat?

12

I've been trying to finetune Llama3 8b with a custom chat dataset, but there seems to be no Llama3 Chat Format class. How can I make a custom one or...

When pushing to this repo, make sure to make a new Netlify project and clone the repo into that.

BERT Model is Inaccurate

4

### System Info - CPU: i9 9900k - GPU: RTX 4090 - TensorRT-LLM Version: 0.9.0.dev2024022000 - Cuda Version: Cuda 12.3 - Driver Version: 545.29.06 - OS: Arch Linux, kernel version...