Synchronizing local compiler cache of Maykeye/TinyLLama-v0
#593
by
tengomucho
HF Staff
- opened
🤖 Neuron Cache Sync Bot
This commit adds newly compiled cache artifacts for the model:
- Original Model ID:
Maykeye/TinyLLama-v0 - Task:
text-generation - Compilation inputs: {'batch_size': 1, 'sequence_length': 128}
- Generated by: tengomucho
- Generated using: Optimum Neuron Model Exporter
These files contain precompiled Neuron-optimized representations of the model, allowing faster loading and inference on AWS Neuron hardware.