diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2023-12-15 19:16:06 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-12-15 19:16:06 -0600 |
| commit | 30a958e5dd6152da0d9e4cf5ce338bd2dd6a0ec4 (patch) | |
| tree | aa505d27e9f68f0e37042ff0eca02ea0486ec537 /README.md | |
| parent | 614842b311a12ac5aba130e165763f997d8ff324 (diff) | |
| download | candle-30a958e5dd6152da0d9e4cf5ce338bd2dd6a0ec4.tar.gz candle-30a958e5dd6152da0d9e4cf5ce338bd2dd6a0ec4.tar.bz2 candle-30a958e5dd6152da0d9e4cf5ce338bd2dd6a0ec4.zip | |
Quantized mixtral model (#1442)
* Add the Mixtral model.
* Add more of the mixtral layers.
* Add the final layers for mixtral.
* Sketch the expert selection.
* Add some expert routing logic.
* Hopefully finish the routing logic for mixtral.
* Add the mixtral example.
* Fix the weight filenames.
* Bugfix.
* Another fix.
* Yet another fix + remove the unused pragma.
* Shape fix.
* Support for quantized mixtral.
* Support mixtral in the quantized example.
* Mlp or moe type.
* Fix the expert field namings.
* Refactor the mlp bit.
* More MoE logic.
* Add the MoE quantized logic.
* Fix the experts length.
Diffstat (limited to 'README.md')
0 files changed, 0 insertions, 0 deletions