Shadowgraph
TrendingBuzzResearch
Chrome extension
Sign in

ISTA-DASLab/Llama-3.2-3B-Instruct-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-3B

0

3 commits

1 linked in READMEs

updated Nov 8, 2024

See the code

README

Official AQLM quantization of meta-llama/Llama-3.2-3B finetuned with PV-Tuning.

For this quantization, we used 2 codebooks of 8 bits and groupsize of 8.

Results:

ModelQuantizationMMLU (5-shot)ArcCArcEHellaswagPiQAWinograndeModel size, Gb
meta-llama/Llama-3.2-3B-Instructfp160.59840.43690.74280.52240.75790.67326.4
2x8g80.48420.36860.70660.48330.72740.63461.5
8-bit
aqlm
conversational
endpoints_compatible
facebook
llama
llama-3
meta
safetensors
text-generation
text-generation-inference
transformers

Similar repos

ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-1B

1

ISTA-DASLab/Llama-3.2-3B-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-3B

0

ISTA-DASLab/Llama-3.2-1B-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-1B

0

ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-2x8-hf

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3.1-8B-Instruct

2

ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3.1-70B-Instruct

45

ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3.1-8B

3

ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3-8B-Instruct

12

ISTA-DASLab/Meta-Llama-3-8B-AQLM-2Bit-1x16

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3-8B

8

Linked in READMEs

Vahe1994/AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive…

1,330

README badge

ISTA-DASLab/Llama-3.2-3B-Instruct-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-3B

0

3 commits

1 linked in READMEs

updated Nov 8, 2024

See the code

README

Official AQLM quantization of meta-llama/Llama-3.2-3B finetuned with PV-Tuning.

For this quantization, we used 2 codebooks of 8 bits and groupsize of 8.

Results:

ModelQuantizationMMLU (5-shot)ArcCArcEHellaswagPiQAWinograndeModel size, Gb
meta-llama/Llama-3.2-3B-Instructfp160.59840.43690.74280.52240.75790.67326.4
2x8g80.48420.36860.70660.48330.72740.63461.5
8-bit
aqlm
conversational
endpoints_compatible
facebook
llama
llama-3
meta
safetensors
text-generation
text-generation-inference
transformers

Similar repos

ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-1B

1

ISTA-DASLab/Llama-3.2-3B-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-3B

0

ISTA-DASLab/Llama-3.2-1B-AQLM-PV-2Bit-2x8

Model

Official AQLM quantization of [meta-llama/Llama-3.2-1B

0

ISTA-DASLab/Meta-Llama-3.1-8B-Instruct-AQLM-PV-2Bit-2x8-hf

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3.1-8B-Instruct

2

ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3.1-70B-Instruct

45

ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3.1-8B

3

ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3-8B-Instruct

12

ISTA-DASLab/Meta-Llama-3-8B-AQLM-2Bit-1x16

Model

Official AQLM quantization of [meta-llama/Meta-Llama-3-8B

8

Linked in READMEs

Vahe1994/AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive…

1,330

README badge