Update configs, add tokenizer

allenai · Mar 19, 2024 · 824c985 · 824c985
1 parent 28719d8
commit 824c985
Show file tree

Hide file tree

Showing 4 changed files with 101,642 additions and 444 deletions.
diff --git a/configs/mcli/mitchish70.yaml b/configs/mcli/mitchish70.yaml
@@ -15,6 +15,13 @@ env_variables:
   OMP_NUM_THREADS: "8"
   LOG_FILTER_TYPE: local_rank0_only
 command: |-
+  # Install AWS CLI (for download unsharded checkpoints).
+  #apt-get update
+  #apt-get install zip unzip
+  #curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"
+  #unzip awscliv2.zip
+  #sudo ./aws/install
+
   # Make sure we have a recent flash-attn.
   # NOTE: only pinning flash-attn here to future proof it.
   pip install flash-attn==2.5.3 --no-build-isolation