SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[doc] use full path for run_qa.py (#34914)

Browse Source 
use full path for run_qa.py
This commit is contained in:
Fanli Lin
2024-11-27 01:23:44 +08:00
committed by GitHub
parent 6bc0c219c1
commit 784d22078a
3 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/source/en/perf_infer_cpu.md
View File

@@ -42,7 +42,6 @@ Enable BetterTransformer with the [`PreTrainedModel.to_bettertransformer`] metho
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder")
model.to_bettertransformer()
```
## TorchScript
@@ -54,7 +53,7 @@ For a gentle introduction to TorchScript, see the [Introduction to PyTorch Torch
With the [`Trainer`] class, you can enable JIT mode for CPU inference by setting the `--jit_mode_eval` flag:
```bash
python run_qa.py \
python examples/pytorch/question-answering/run_qa.py \
--model_name_or_path csarron/bert-base-uncased-squad-v1 \
--dataset_name squad \
--do_eval \
@@ -86,7 +85,7 @@ pip install intel_extension_for_pytorch
Set the `--use_ipex` and `--jit_mode_eval` flags in the [`Trainer`] class to enable JIT mode with the graph optimizations:
```bash
python run_qa.py \
python examples/pytorch/question-answering/run_qa.py \
--model_name_or_path csarron/bert-base-uncased-squad-v1 \
--dataset_name squad \
--do_eval \