AntMan/vicuna-v1.3-7b-space

Model

This is the Vicuna-7B model trained with SPACE for inference acceleration. It achieves more than 2x inference speedup. For details, please visit github.

0

3 commits

2 linked in READMEs

updated May 19, 2024

README

This is the Vicuna-7B model trained with SPACE for inference acceleration. It achieves more than 2x inference speedup. For details, please visit github.

license: apache-2.0

endpoints_compatible

llama

pytorch

text-generation

text-generation-inference

transformers

Contributors

3 commits

Similar repos

mit-han-lab/vicuna-7b-v1.5-QServe-g128

0

LLMs/Vicuna-7b-v1.1

2

mit-han-lab/vicuna-7b-v1.5-QServe

0

mit-han-lab/vicuna-13b-v1.5-QServe

0

squeeze-ai-lab/sq-vicuna-7b-v1.3-w3-s0

0

squeeze-ai-lab/sq-vicuna-7b-v1.3-w4-s0

0

mit-han-lab/vicuna-13b-v1.5-QServe-g128

0

Vision-CAIR/vicuna-7b

25

Linked in READMEs

hemingkx/Spec-Bench

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL…

414

cteant/SPACE

Official implementation of SPACE

10

AntMan/vicuna-v1.3-7b-space

Model

This is the Vicuna-7B model trained with SPACE for inference acceleration. It achieves more than 2x inference speedup. For details, please visit github.

0

3 commits

2 linked in READMEs

updated May 19, 2024

README

This is the Vicuna-7B model trained with SPACE for inference acceleration. It achieves more than 2x inference speedup. For details, please visit github.

license: apache-2.0

endpoints_compatible

llama

pytorch

text-generation

text-generation-inference

transformers

Similar repos

mit-han-lab/vicuna-7b-v1.5-QServe-g128

0

LLMs/Vicuna-7b-v1.1

2

mit-han-lab/vicuna-7b-v1.5-QServe

0

mit-han-lab/vicuna-13b-v1.5-QServe

0

squeeze-ai-lab/sq-vicuna-7b-v1.3-w3-s0

0

squeeze-ai-lab/sq-vicuna-7b-v1.3-w4-s0

0

mit-han-lab/vicuna-13b-v1.5-QServe-g128

0

Vision-CAIR/vicuna-7b

25

Linked in READMEs

hemingkx/Spec-Bench

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL…

414

cteant/SPACE

Official implementation of SPACE

10

Contributors

3 commits