Closed tirthasheshpatel closed 5 months ago
This PR adds the LLaMA Causal LM along with a weight conversion script for the 7B presets (LLaMA 7B and LLaMA Chat 7B).
Tested that the outputs of the models match with 1e-4 tolerance on CPU and float32.
1e-4
float32
TODO:
Changes on master are breaking the tests in this PR. Will sync and push the final changes.
Thanks!
This PR adds the LLaMA Causal LM along with a weight conversion script for the 7B presets (LLaMA 7B and LLaMA Chat 7B).
Tested that the outputs of the models match with
1e-4
tolerance on CPU andfloat32
.TODO: