可亲
fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm
688e28d
- SHA256:
- cd4076e8117ce301d7488c2707cc5dea92e726956fd4060b38087d293405b030
- Pointer size:
- 135 Bytes
- Size of remote file:
- 3.91 GB
- Xet backed hash:
- 2f6781a1717dcd96d2cf1fa0bf288c8232b62cd5434c1eb776f9e900804ad430
·
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.