Charlie Ruan

@darvid Updated to 0.2.10 to reflect tokenizer's 0.1.2. Sorry for the delay

The `/resolve` should be correct; the unmatching model id might caused the issue. Let me know if this fixed it: https://github.com/mlc-ai/web-llm/pull/317 Thanks!

Which browser are you using? We're mostly tested on Chrome -- e.g. for the latest version of Chrome, Macbooks do not need any flag to run things. You could also...

I see; not sure if using [Chrome Canary](https://www.google.com/chrome/canary/) would make things easier (e.g. not needing the flags). Regarding shader-f16, try using models that have `f32` rather than `f16`. You can...

Closing this issue for now due to inactivity. Feel free to reopen or open another issue if there are other questions!

Hi @localagi, if the model you are interested in has architecture supported by MLC-LLM, but the model itself is not explicitly supported, you can follow the tutorial [Distribute Compiled Model](https://mlc.ai/mlc-llm/docs/compilation/distribute_compiled_models.html)...

I had this error because I accidentally removed `--deepspeed ./scripts/zero2.json \` from the provided finetune script. Alternatively, perhaps adding the following lines at the start of `train()` in `train.py` may...

This error should be addressed in npm 0.2.36. For details please see https://github.com/mlc-ai/web-llm/pull/397.

Closing this issue as completed; feel free to open new ones if problems persist

It should be fixed now via https://github.com/mlc-ai/mlc-llm/pull/2187. We recently used EMCC to include runtime code from https://github.com/mlc-ai/mlc-llm into the model WASM; as of now mainly for the grammar usages. Currently,...