Where is the source code for vicuna-7b_webgpu.wasm?

[zeritonius]

Where is the source code for vicuna-7b_webgpu.wasm, please?

Thank you.

[jinhongyii]

We will post a tutorial on how to build the model into generated source code, but currently that's not ready until we migrate the vicuna-v0 to vicuna-v1.1 (The reason is that vicuna-v0 is deprecated and it's complicated to get its weight compared with v1.1). Do you want a link to the generated code in .wgsl format right now?

[zeritonius]

I will wait for that tutorial. Thank you for the info.

[Ryan-yang125]

hi, you can find it in https://github.com/mlc-ai/web-llm/tree/gh-pages/docs/dist/vicuna-7b

[zeritonius]

@Ryan-yang125 At the above location, I found the compiled file | the executable (.wasm), but not the text file | the source file (.wat). Do I need a special kind of access to see the .wat file?

Thank you.

[jinhongyii]

Thanks for your patience. We've just added an instruction for building models and deploy locally. Feel free to check it out. The wasm filet will be under dist/vicuna-7b-v1 after running build.py

[jinhongyii]

Additional info to get source code, run

python3 build.py --target webgpu --debug-dump

you will see the IR and wgsl file under dist/vicuna-7b-v1/debug