Yan Zhabin

Is it hard just to review and close some PR's. It won't take so much time.

Common guys. Is it so complicated to apply this only line? `config = yaml.load(fd, Loader=yaml.SafeLoader)`

I have the same issue.

I've converted it, and it works well ```sh python3 -m mlc_llm.build --hf-path openchat/openchat_3.5 --target metal_x86_64 --quantization q4f16_1 ``` I have only 1 issue the model doesn't stop streaming sometimes (like...

@alpayariyak Uploaded to HF ## OpenChat 3.5 https://huggingface.co/iyanello/openchat_3.5-q4f16_1-mlc-llm ## OpenChat 3.5 - 1210 update https://huggingface.co/iyanello/openchat_3.5-1210-q4f16_1-mlc-llm/tree/main

https://github.com/mlc-ai/mlc-llm/issues/1776#issuecomment-1992550167

Any updates?

@tqchen Does a new engine still support custom or modified chat/conversation templates in MLC config? For example, sometimes there are differences between the original model and the fine-tuned model.

It would be nice to update `define new models` section as well.

Actually it works well even now with the current new flow. It just needs _in few_ adjustments. Because it's just tuned mistral architecture, and it's supported by `mlc`. Here is...