We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 783c08f commit 36416e1Copy full SHA for 36416e1
README.md
@@ -132,7 +132,7 @@ pip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu121
132
pip install vllm==0.6.3 ray
133
pip install flash-attn --no-build-isolation
134
pip install -e . # For verl integration
135
-pip install wandb IPython matplotlib sqlparse func_timeout
+pip install wandb IPython matplotlib sqlparse func_timeout nltk ijson
136
```
137
138
4. Download the model weights from HuggingFace and put them in the `models/` directory.
requirements.txt
@@ -4,7 +4,9 @@ datasets
4
dill
5
flash-attn
6
hydra-core
7
+ijson
8
numpy
9
+nltk
10
pandas
11
pybind11
12
ray
0 commit comments