可亲
fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm
288c348
- SHA256:
- ccb329fd14b0ca16bc1b14a58e8a859fa3a6f2905a03388be9b92bc955346c2a
- Pointer size:
- 135 Bytes
- Size of remote file:
- 4 GB
- Xet hash:
- 301de5b82a6dda32d1a78ca6c39f1fad47bf4d9a6c94ab2c6adca8d1ff006be7
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.