7b CodeLlama model finetuned on the entire PIE dataset unconditionally to optimize C++ programs. For more details on how the data was collected and training was done, refer to this webpage.

Downloads last month
23
Safetensors
Model size
6.74B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for LearningOpt/pie-all-uncon-7b

Quantizations
1 model