Download inference-cache-config/gpt2.json from aws-neuron/optimum-neuron-cache: direct link, hf CLI and curl.
- Browser
- Download file 398 Bytes
-
https://huggingface.co/aws-neuron/optimum-neuron-cache/resolve/a6e63d1d53aef98995ec00a7895a4bbbb9abcaa2/inference-cache-config/gpt2.json
- Command line
-
hf download hf://aws-neuron/optimum-neuron-cache@a6e63d1d53aef98995ec00a7895a4bbbb9abcaa2/inference-cache-config/gpt2.json
-
curl -L -o gpt2.json https://huggingface.co/aws-neuron/optimum-neuron-cache/resolve/a6e63d1d53aef98995ec00a7895a4bbbb9abcaa2/inference-cache-config/gpt2.json
398 Bytes
| { | |
| "openai-community/gpt2": [ | |
| { | |
| "batch_size": 1, | |
| "sequence_length": 1024, | |
| "num_cores": 2, | |
| "auto_cast_type": "fp16" | |
| }, | |
| { | |
| "batch_size": 4, | |
| "sequence_length": 1024, | |
| "num_cores": 2, | |
| "auto_cast_type": "fp16" | |
| }, | |
| { | |
| "batch_size": 16, | |
| "sequence_length": 1024, | |
| "num_cores": 2, | |
| "auto_cast_type": "fp16" | |
| } | |
| ] | |
| } |