Jesse Andrews

Enhancement: support larger file download

3

@daanelson has shared that https://storage.googleapis.com/replicate-weights/llama-13b-fp16.tensors which is ~24GB. To compare, `gcloud` can download this in parallel between 1-2 GBps

not ready for merge yet, but you can try it by setting `--llava True`

`cog serve` on your development cog will start both your cog & proxy that serve a local playground react app `cog serve r8.im/anotherjesse/sdxl-lcm-testing` will download the cog image and then...

after chatting with @pvh, having automerge run in a worker is probably overkill/adds complexity in a world where automerge is faster (and WASM/rust automerge is 'coming soon') My approach to...

also the parser was including the surrounding " for strings... Those should (probably) be removed https://bsky.app/profile/anotherjesse.com/post/3lbwtom3wi22l