diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2024-02-22 23:23:46 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-22 23:23:46 +0200 |
| commit | 96633eeca1265ed03e57230de54032041c58f9cd (patch) | |
| tree | f3e0370d7f304666030968a4f0fb8a36f693b605 /examples/llama.swiftui/llama.cpp.swift/LibLlama.swift | |
| parent | 847eedbdb2d1ebf14ef56eb507d4b4b975510908 (diff) | |
gemma : use more bits for the token_embd.weight tensor (#5650)
* gemma : use Q8_0 for the token_embd.weight tensor
* llama : quantize token_embd.weight using output type
Diffstat (limited to 'examples/llama.swiftui/llama.cpp.swift/LibLlama.swift')
0 files changed, 0 insertions, 0 deletions