llama factory

redhat/ocp4/4.16/2024.12.llama.factory.md

@@ -3,7 +3,65 @@
 
 # build image
 
-# run multiple instance using deployment
+on vm, with 16C 32G.
+
+```bash
+
+# download the model first
+dnf install -y conda
+
+
+mkdir -p /data/env/
+conda create -y -p /data/env/hg_cli python=3.11
+
+conda init bash
+
+conda activate /data/env/hg_cli
+# conda deactivate
+
+# python -m pip install --upgrade pip setuptools wheel
+
+pip install --upgrade huggingface_hub
+
+
+# for Maykeye/TinyLLama-v0
+VAR_NAME=Maykeye/TinyLLama-v0
+
+VAR_NAME_FULL=${VAR_NAME//\//-}
+echo $VAR_NAME_FULL
+# THUDM-ChatGLM2-6B
+
+mkdir -p /data/huggingface/${VAR_NAME_FULL}
+cd /data/huggingface/${VAR_NAME_FULL}
+
+while true; do
+    huggingface-cli download --repo-type model --revision main --cache-dir /data/huggingface/cache --local-dir ./ --local-dir-use-symlinks False --exclude "*.pt"  --resume-download ${VAR_NAME} 
+    if [ $? -eq 0 ]; then
+        break
+    fi
+    sleep 1  # Optional: waits for 1 second before trying again
+done
+
+
+# install and try llama factory
+mkdir -p /data/git
+cd /data/git
+
+git clone -b wzh https://github.com/wangzheng422/LLaMA-Factory
+
+cd /data/git/LLaMA-Factory
+
+pip install -e ".[torch,metrics]"
+
+
+/bin/rm -rf saves/tinyllama
+llamafactory-cli train wzh/tinyllama_lora_sft.yaml
+
+
+
+```
+
+# run multiple instance using deployment on ocp
 
 
 # end