Skip to content

Commit

Permalink
convert wget to curl since wget not available on all hosts (#823)
Browse files Browse the repository at this point in the history
* missed some wget

* convert wget to curl for gguf

* Update docs/native-execution.md

Co-authored-by: Nikita Shulga <[email protected]>

---------

Co-authored-by: Nikita Shulga <[email protected]>
  • Loading branch information
mikekgfb and malfet committed Jul 17, 2024
1 parent 9e52152 commit 7b473a0
Show file tree
Hide file tree
Showing 2 changed files with 7 additions and 6 deletions.
9 changes: 5 additions & 4 deletions docs/GGUF.md
Original file line number Diff line number Diff line change
Expand Up @@ -28,11 +28,12 @@ and F32.)
```
# Download resources
mkdir -p ggufs/open_orca
cd ggufs/open_orca
wget -O open_orca.Q4_0.gguf "https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GGUF/resolve/main/tinyllama-1.1b-1t-openorca.Q4_0.gguf?download=true"
pushd ggufs/open_orca
wget -O tokenizer.model "https://github.com/karpathy/llama2.c/raw/master/tokenizer.model"
cd ../..
curl -o open_orca.Q4_0.gguf "https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GGUF/resolve/main/tinyllama-1.1b-1t-openorca.Q4_0.gguf?download=true"
curl -o ./tokenizer.model https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
popd
export GGUF_MODEL_PATH=ggufs/open_orca/open_orca.Q4_0.gguf
export GGUF_TOKENIZER_PATH=ggufs/open_orca/tokenizer.model
Expand Down
4 changes: 2 additions & 2 deletions docs/native-execution.md
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ python3 torchchat.py export stories15M --output-dso-path ./model.so
We can now execute the runner with:

```
wget -O ./tokenizer.model https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
curl -OL https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
./cmake-out/aoti_run ./model.so -z ./tokenizer.model -l 2 -i "Once upon a time"
```

Expand Down Expand Up @@ -104,7 +104,7 @@ python3 torchchat.py export stories15M --output-pte-path ./model.pte
We can now execute the runner with:

```
wget -O ./tokenizer.model https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
curl -o ./tokenizer.model https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
./cmake-out/et_run ./model.pte -z ./tokenizer.model -l 2 -i "Once upon a time"
```

Expand Down

0 comments on commit 7b473a0

Please sign in to comment.