d-matrix-ai

.github

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

dmx-compressor

d-Matrix DMX Compressor: A Pytorch toolkit for nn.Module transformations supporting advanced quantization, sparsity, and elementwise function approximations.

gptq

Code for the paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers"

keyformer-llm

lm-evaluation-harness-nikita

A framework for few-shot evaluation of language models.

mlperf-hf

mlperf-hf

d-matrix-ai/keyformer-llm

d-matrix-ai/dmx-compressor

d-Matrix DMX Compressor: A Pytorch toolkit for nn.Module transformations supporting advanced quantization, sparsity, and elementwise function approximations.

d-matrix-ai/.github

d-matrix-ai/bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

d-matrix-ai/gptq

Code for the paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers"

d-matrix-ai/lm-evaluation-harness-nikita

A framework for few-shot evaluation of language models.

d-matrix-ai/mlperf-hf

mlperf-hf