PR #7481 llama: extend for small granite models

llama: extend for small granite models #7481

ggerganov merged 3 commits into ggml-org:master from giuseppe:fix-granite-3b

github-actions added python

giuseppe force pushed 1 year ago

mofosyne added Review Complexity : Medium

mofosyne added model

ggerganov commented on 2024-05-23

giuseppe force pushed 1 year ago

giuseppe changed the title ~~llama: define architecture for granite models~~ llama: define architecture for small granite models 1 year ago

giuseppe force pushed 1 year ago

compilade commented on 2024-05-24

giuseppe force pushed 1 year ago

Add optional MLP bias for Granite models

120f7bf5

giuseppe force pushed 1 year ago

ggerganov commented on 2024-05-26

giuseppe changed the title ~~llama: define architecture for small granite models~~ llama: extend for small granite models 1 year ago

llama: honor add_space_prefix from the model configuration

06748ff3

llama: add support for small granite models

b974e9fc

giuseppe force pushed to b974e9fc 1 year ago

ggerganov approved these changes on 2024-05-28

ggerganov merged 5442939f into master 1 year ago

Reviewers

ggerganov

compilade

Assignees

No one assigned

Labels

model python Review Complexity : Medium

Milestone

No milestone