Qwen3-4B-Thinking-2507 / model.litertlm

GPU graph re-ship: KV-cache update and attention rewritten into the runtime's GPU composite ops plus a 16-token prefill signature; weights, tokenizer and metadata byte-identical; CPU output bit-identical (card and manifest updated)

f8ce479 verified 18 days ago

History Blame Contribute Delete

2.48 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 7e0e3aeb8754a166de16fa3b7743fac36116fdbe151386ac30ae2fd5469d714e
Size of remote file:: 2.48 GB
SHA256:: 8a8a6a419a5570b3f4814d358fb795c0dcb6931206c7dae29480f47564c3f04d

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.