Statements (17)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:large_language_model
|
| gptkbp:compatibleWith |
gptkb:horse_race
gptkb:Llama_2 other transformer-based LLMs |
| gptkbp:developedBy |
gptkb:Tencent_AI_Lab
|
| gptkbp:enables |
faster inference
lower memory usage |
| gptkbp:license |
Apache 2.0
|
| gptkbp:openSource |
true
|
| gptkbp:purpose |
efficient quantization of large language models
|
| gptkbp:releaseYear |
2023
|
| gptkbp:repository |
https://github.com/mit-han-lab/llm-awq
|
| gptkbp:supports |
int4 quantization
int8 quantization |
| gptkbp:bfsParent |
gptkb:Indonesia_AirAsia
|
| gptkbp:bfsLayer |
6
|
| https://www.w3.org/2000/01/rdf-schema#label |
AWQ
|