336f75409d
Model: saarvajanik/facebook-opt-6.7b-qcqa-ub-16-best-for-KV-cache Source: Original Platform
8 lines
418 B
Markdown
8 lines
418 B
Markdown
---
|
|
license: mit
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
---
|
|
|
|
This is a GQA version of the original model facebook/opt-125m. In this version, the original MHA architecture is preserved but instead of having a single K/V head, different K/V heads corresponding to the same group have the same mean-pooled K or V values. It has 16 groups of KV heads per layer instead of original 32 KV heads in the MHA implementation. |