Laurent Mazare deee7612da Quantized version of mistral. (#1009) ...

* Quantized version of mistral.

* Integrate the quantized mistral variant.

* Use the quantized weight files.

* Tweak the quantization command.

* Fix the dtype when computing the rotary embeddings.

* Update the readme with the quantized version.

* Fix the decoding of the remaining tokens.

2023-09-30 18:25:47 +01:00

..

basics.rs

Dilated convolutions (#657)

2023-08-29 16:12:11 +01:00

cuda_basics.rs

Dilated convolutions (#657)

2023-08-29 16:12:11 +01:00

cuda_sum_benchmark.rs

More accelerate optimizations (#427)

2023-08-13 12:53:34 +01:00

tensor-tools.rs

Quantized version of mistral. (#1009)

2023-09-30 18:25:47 +01:00