llama factory

wangzheng422 · Jan 2, 2025 · 3e24340 · 3e24340
1 parent f6ae616
commit 3e24340
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 6 deletions.
diff --git a/redhat/ocp4/4.16/2024.12.llama.factory.md b/redhat/ocp4/4.16/2024.12.llama.factory.md
@@ -137,13 +137,15 @@ But this will not stop us, our target is to run the multiple node task using `ra
 
 ```bash
 
-podman build -t quay.io/wangzheng422/qimgs:llama-factory-ray-20241226-v01 -f wzh/ray.dockerfile .
+cd /data/git/LLaMA-Factory
+
+podman build -t quay.io/wangzheng422/qimgs:llama-factory-ray-20250102-v02 -f wzh/ray.dockerfile .
 
 
-podman run --rm -it quay.io/wangzheng422/qimgs:llama-factory-ray-20241226-v01 /bin/bash
+podman run --rm -it quay.io/wangzheng422/qimgs:llama-factory-ray-20250102-v02 /bin/bash
 
 
-podman push quay.io/wangzheng422/qimgs:llama-factory-ray-20241226-v01
+podman push quay.io/wangzheng422/qimgs:llama-factory-ray-20250102-v02
 
 ```
 

diff --git a/redhat/ocp4/4.16/files/ray.notebook/2.5_run.llama.factory.ipynb b/redhat/ocp4/4.16/files/ray.notebook/2.5_run.llama.factory.ipynb
@@ -30,7 +30,7 @@
     "# IF unused, SDK will automatically check for default kubeconfig, then in-cluster config\n",
     "# KubeConfigFileAuthentication can also be used to specify kubeconfig path manually\n",
     "auth = TokenAuthentication(\n",
-    "    token = \"sha256~KAuGVI_ujl_uq57sVrOtMUN8VuNjbO00FG6P-vbhv2A\",\n",
+    "    token = \"sha256~DVnZ1tbr11kPu9ltluH0M_Xa3O_6dEKFZScmvHuio1Y\",\n",
     "    server = \"https://api.demo-01-rhsys.wzhlab.top:6443\",\n",
     "    skip_tls= True\n",
     ")\n",
@@ -75,7 +75,7 @@
     "    worker_cpu_limits=1,\n",
     "    worker_memory_requests=4,\n",
     "    worker_memory_limits=6,\n",
-    "    image=\"quay.io/wangzheng422/qimgs:llama-factory-ray-20241226-v01\", # Optional Field \n",
+    "    image=\"quay.io/wangzheng422/qimgs:llama-factory-ray-20250102-v02\", # Optional Field \n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",
     "))"
@@ -192,7 +192,7 @@
     "import subprocess\n",
     "import re\n",
     "\n",
-    "@ray.remote\n",
+    "@ray.remote(memory=4 * 1024 * 1024 * 1024)  # 4 GB memory limit\n",
     "class NetworkCommandActor:\n",
     "    def get_eth0_ip(self):\n",
     "        try:\n",