github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[fix] fix grok-1 example typo (#5506)

pull/5515/head
Yuanheng Zhao 2024-03-26 10:19:42 +08:00 committed by GitHub
parent 0688d92e2d
commit 131f32a076
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/language/grok-1/README.md
View File

@ -35,7 +35,7 @@ Command example:
./run_inference_slow.sh <MODEL_NAME_OR_PATH> ./run_inference_slow.sh <MODEL_NAME_OR_PATH>
``` ```
`MODEL_NAME_OR_PATH` can be a model name from Hugging Face model hub or a local path to PyTorch-version model checkpoints. We provided weights on model hub, named `hpcaitech/grok-1`. And you could also download the weights in advance using `git`: `MODEL_NAME_OR_PATH` can be a model name from Hugging Face model hub or a local path to PyTorch-version model checkpoints. We have provided pytorch-version checkpoint on [HuggingFace model hub](https://huggingface.co/hpcai-tech/grok-1), named `hpcai-tech/grok-1`. And you could also download the weights in advance using `git`:
```bash ```bash
git lfs install git lfs install
git clone https://huggingface.co/hpcai-tech/grok-1 git clone https://huggingface.co/hpcai-tech/grok-1

2
examples/language/grok-1/run_inference_fast.sh
View File

@ -1,6 +1,6 @@
#!/usr/bin/env bash #!/usr/bin/env bash
PRETRAINED=${1:-"hpcaitech/grok-1"} PRETRAINED=${1:-"hpcai-tech/grok-1"}
torchrun --standalone --nproc_per_node 8 inference_tp.py --pretrained "$PRETRAINED" \ torchrun --standalone --nproc_per_node 8 inference_tp.py --pretrained "$PRETRAINED" \
--max_new_tokens 100 \ --max_new_tokens 100 \

2
examples/language/grok-1/run_inference_slow.sh
View File

@ -1,6 +1,6 @@
#!/usr/bin/env bash #!/usr/bin/env bash
PRETRAINED=${1:-"hpcaitech/grok-1"} PRETRAINED=${1:-"hpcai-tech/grok-1"}
python3 inference.py --pretrained "$PRETRAINED" \ python3 inference.py --pretrained "$PRETRAINED" \
--max_new_tokens 100 \ --max_new_tokens 100 \