diff --git "a/Untitled1.ipynb" "b/Untitled1.ipynb"
--- "a/Untitled1.ipynb"
+++ "b/Untitled1.ipynb"
@@ -76,7 +76,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "id": "4a7a57e8-6bc3-4d15-88ac-942e8347b7cd",
    "metadata": {},
    "outputs": [
@@ -84,7 +84,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Loading checkpoint shards: 100%|██████████| 4/4 [00:31<00:00,  7.82s/it]\n"
+      "Loading checkpoint shards: 100%|██████████| 4/4 [00:20<00:00,  5.04s/it]\n"
      ]
     },
     {
@@ -99,7 +99,7 @@
     "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
     "\n",
     "# Path to your local checkpoint directory\n",
-    "checkpoint_path = \"checkpoint-80\"\n",
+    "checkpoint_path = \"checkpoint-162\"\n",
     "\n",
     "# Load the model and tokenizer\n",
     "model = AutoModelForCausalLM.from_pretrained(checkpoint_path)\n",
@@ -111,17 +111,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
    "id": "c3b9fcde-a4f3-4217-ba9a-cf799800cd63",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "RepoUrl('https://huggingface.co/neginashz/checkpoint-80', endpoint='https://huggingface.co', repo_type='model', repo_id='neginashz/checkpoint-80')"
+       "RepoUrl('https://huggingface.co/neginashz/checkpoint-162', endpoint='https://huggingface.co', repo_type='model', repo_id='neginashz/checkpoint-162')"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -129,2169 +129,34 @@
    "source": [
     "from huggingface_hub import create_repo\n",
     "\n",
-    "create_repo(repo_id=\"neginashz/checkpoint-80\", private=False, exist_ok=True)\n"
+    "create_repo(repo_id=\"neginashz/checkpoint-162\", private=False, exist_ok=True)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "id": "6e19721a-b69c-42e6-a740-04e4b8ded4fa",
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Upload 7 LFS files:   0%|          | 0/7 [00:00<?, ?it/s]\n",
-      "model-00002-of-00007.safetensors:   0%|          | 0.00/4.78G [00:00<?, ?B/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 0.00/4.93G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 0.00/5.00G [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 0.00/4.98G [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 0.00/4.93G [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 8.19k/4.78G [00:00<18:04:53, 73.4kB/s]\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 1.56M/4.78G [00:00<09:15, 8.60MB/s]   \u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 8.19k/5.00G [00:00<28:58:20, 47.9kB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 8.19k/4.93G [00:00<31:12:11, 43.9kB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 8.19k/4.98G [00:00<28:07:33, 49.2kB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 8.19k/4.93G [00:00<26:32:34, 51.6kB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 3.70M/4.78G [00:00<06:05, 13.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 1.74M/5.00G [00:00<11:28, 7.26MB/s]   \u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 1.58M/4.93G [00:00<13:01, 6.31MB/s]   \u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 1.47M/4.93G [00:00<11:47, 6.97MB/s]   \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 1.79M/4.98G [00:00<11:23, 7.28MB/s]   \u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 6.55M/4.78G [00:00<04:15, 18.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 3.94M/5.00G [00:00<06:32, 12.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 3.36M/4.93G [00:00<07:53, 10.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 3.31M/4.93G [00:00<07:07, 11.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 3.74M/4.98G [00:00<07:01, 11.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 8.46M/4.78G [00:00<04:16, 18.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 5.64M/5.00G [00:00<05:51, 14.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 5.28M/4.93G [00:00<06:08, 13.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 5.41M/4.93G [00:00<05:29, 15.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 5.73M/4.98G [00:00<05:41, 14.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 7.40M/5.00G [00:00<05:26, 15.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 10.4M/4.78G [00:00<04:16, 18.6MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 7.21M/4.93G [00:00<05:21, 15.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 7.51M/4.93G [00:00<04:49, 17.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 7.48M/4.98G [00:00<05:20, 15.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 9.07M/5.00G [00:00<05:16, 15.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 12.2M/4.78G [00:00<04:21, 18.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 9.36M/4.93G [00:00<04:41, 17.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 8.86M/4.93G [00:00<05:19, 15.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 9.21M/4.98G [00:00<05:09, 16.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 11.1M/5.00G [00:00<04:52, 17.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 11.5M/4.93G [00:00<04:22, 18.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 14.1M/4.78G [00:00<04:24, 18.0MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 10.8M/4.93G [00:00<04:55, 16.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 11.1M/4.98G [00:00<04:54, 16.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 12.9M/5.00G [00:00<04:46, 17.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 13.4M/4.93G [00:00<04:24, 18.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 12.9M/4.93G [00:00<04:35, 17.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 12.9M/4.98G [00:00<04:48, 17.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 15.7M/5.00G [00:00<04:02, 20.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 15.7M/4.93G [00:01<03:53, 21.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 16.0M/4.78G [00:01<06:20, 12.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 16.0M/4.98G [00:01<04:23, 18.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 16.0M/4.93G [00:01<04:45, 17.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 17.7M/5.00G [00:01<04:23, 18.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 17.9M/4.93G [00:01<04:27, 18.4MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 18.7M/4.78G [00:01<05:05, 15.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 18.1M/4.98G [00:01<04:15, 19.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 17.8M/4.93G [00:01<05:02, 16.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 20.2M/5.00G [00:01<04:03, 20.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 19.8M/4.93G [00:01<04:26, 18.4MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 21.4M/4.78G [00:01<04:19, 18.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 20.3M/4.98G [00:01<04:07, 20.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 19.6M/4.93G [00:01<04:54, 16.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 22.5M/5.00G [00:01<03:56, 21.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 22.3M/4.93G [00:01<04:03, 20.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   0%|          | 23.5M/4.78G [00:01<04:20, 18.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 22.3M/4.98G [00:01<04:24, 18.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 21.8M/4.93G [00:01<04:31, 18.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   0%|          | 24.6M/5.00G [00:01<04:08, 20.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   0%|          | 24.4M/4.93G [00:01<04:13, 19.4MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 25.5M/4.78G [00:01<04:17, 18.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   0%|          | 23.7M/4.93G [00:01<04:28, 18.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   0%|          | 24.2M/4.98G [00:01<04:39, 17.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 26.6M/5.00G [00:01<04:09, 19.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 26.5M/4.93G [00:01<04:07, 19.9MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 27.5M/4.78G [00:01<04:18, 18.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 25.6M/4.93G [00:01<04:34, 17.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 26.0M/4.98G [00:01<04:38, 17.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 28.6M/5.00G [00:01<04:16, 19.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 28.5M/4.93G [00:01<04:13, 19.4MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 29.4M/4.78G [00:01<04:15, 18.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 27.7M/4.93G [00:01<04:20, 18.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 27.8M/4.98G [00:01<04:41, 17.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 30.6M/5.00G [00:01<04:17, 19.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 30.5M/4.93G [00:01<04:19, 18.9MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 31.3M/4.78G [00:01<04:24, 17.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 29.6M/4.98G [00:01<04:39, 17.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 29.6M/4.93G [00:01<04:27, 18.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 32.4M/4.93G [00:01<04:56, 16.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 32.5M/5.00G [00:01<05:40, 14.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 32.0M/4.98G [00:01<05:05, 16.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 33.1M/4.78G [00:02<05:51, 13.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 32.0M/4.93G [00:02<05:35, 14.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 35.7M/4.93G [00:02<03:56, 20.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 35.5M/5.00G [00:02<04:32, 18.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 34.2M/4.98G [00:02<04:41, 17.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 34.7M/4.78G [00:02<05:55, 13.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 33.9M/4.93G [00:02<05:12, 15.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 38.3M/5.00G [00:02<04:01, 20.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 36.6M/4.98G [00:02<04:14, 19.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 37.8M/4.93G [00:02<04:19, 18.9MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 36.4M/4.78G [00:02<05:30, 14.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 35.6M/4.93G [00:02<05:12, 15.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 38.7M/4.98G [00:02<04:10, 19.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 40.5M/5.00G [00:02<04:12, 19.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 39.8M/4.93G [00:02<04:32, 18.0MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 38.4M/4.78G [00:02<05:03, 15.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 37.3M/4.93G [00:02<05:09, 15.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 40.7M/4.98G [00:02<04:07, 20.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 42.6M/5.00G [00:02<04:08, 20.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 41.7M/4.93G [00:02<04:29, 18.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 40.3M/4.78G [00:02<04:47, 16.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 39.0M/4.93G [00:02<05:10, 15.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 42.8M/4.98G [00:02<04:04, 20.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 44.7M/5.00G [00:02<04:14, 19.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 43.6M/4.93G [00:02<04:30, 18.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 42.0M/4.78G [00:02<04:47, 16.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 40.7M/4.93G [00:02<05:04, 16.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 44.9M/4.98G [00:02<04:09, 19.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 46.7M/5.00G [00:02<04:17, 19.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 45.4M/4.93G [00:02<04:36, 17.7MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 43.7M/4.78G [00:02<04:50, 16.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 42.3M/4.93G [00:02<05:11, 15.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 47.1M/4.98G [00:02<04:01, 20.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 47.9M/4.93G [00:02<04:10, 19.5MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 47.9M/4.78G [00:02<03:20, 23.6MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 51.9M/4.93G [00:02<03:14, 25.1MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 49.1M/4.98G [00:02<04:38, 17.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 48.7M/5.00G [00:02<05:56, 13.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 48.0M/4.93G [00:02<03:55, 20.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 54.9M/4.93G [00:02<03:05, 26.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 51.0M/4.98G [00:02<04:40, 17.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 50.8M/5.00G [00:02<05:22, 15.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 50.4M/4.78G [00:03<04:24, 17.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 50.0M/4.93G [00:02<03:58, 20.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 53.1M/4.98G [00:03<04:25, 18.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 52.9M/5.00G [00:03<04:56, 16.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 57.5M/4.93G [00:03<03:20, 24.3MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 52.4M/4.78G [00:03<04:19, 18.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 52.1M/4.93G [00:03<03:57, 20.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 55.0M/4.98G [00:03<04:23, 18.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 54.9M/5.00G [00:03<04:42, 17.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 54.4M/4.78G [00:03<04:16, 18.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 54.2M/4.93G [00:03<03:55, 20.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|          | 60.0M/4.93G [00:03<03:38, 22.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 56.9M/4.98G [00:03<04:24, 18.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 56.9M/5.00G [00:03<04:32, 18.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 56.5M/4.78G [00:03<04:08, 19.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 56.4M/4.93G [00:03<03:53, 20.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|▏         | 62.3M/4.93G [00:03<03:45, 21.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 58.9M/4.98G [00:03<04:17, 19.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 59.0M/5.00G [00:03<04:19, 19.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|          | 58.5M/4.78G [00:03<04:04, 19.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 58.5M/4.93G [00:03<03:51, 21.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|          | 61.7M/4.98G [00:03<03:46, 21.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|          | 62.0M/5.00G [00:03<03:44, 22.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|▏         | 61.1M/4.78G [00:03<03:45, 20.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|          | 61.1M/4.93G [00:03<03:36, 22.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|▏         | 64.5M/4.93G [00:03<04:49, 16.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|▏         | 63.9M/4.98G [00:03<03:52, 21.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|▏         | 63.4M/4.78G [00:03<03:39, 21.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|▏         | 63.5M/4.93G [00:03<03:32, 22.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   1%|▏         | 70.0M/4.93G [00:03<03:32, 22.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|▏         | 64.3M/5.00G [00:03<05:06, 16.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|▏         | 65.8M/4.93G [00:03<03:54, 20.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 74.5M/4.93G [00:03<02:54, 27.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|▏         | 66.8M/5.00G [00:03<04:33, 18.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|▏         | 65.6M/4.78G [00:03<04:55, 16.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|▏         | 68.4M/4.93G [00:03<03:40, 22.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|▏         | 66.1M/4.98G [00:03<06:27, 12.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|▏         | 68.8M/5.00G [00:03<04:30, 18.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|▏         | 67.4M/4.78G [00:03<04:44, 16.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|▏         | 70.6M/4.93G [00:03<03:39, 22.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 77.5M/4.93G [00:03<03:23, 23.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|▏         | 68.1M/4.98G [00:03<05:47, 14.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|▏         | 69.5M/4.78G [00:04<04:29, 17.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|▏         | 70.8M/5.00G [00:04<04:33, 18.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   1%|▏         | 72.9M/4.93G [00:04<03:43, 21.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|▏         | 70.4M/4.98G [00:04<05:03, 16.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   1%|▏         | 71.7M/4.78G [00:04<04:12, 18.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   1%|▏         | 73.4M/5.00G [00:04<04:05, 20.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 75.5M/4.93G [00:04<03:30, 23.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   1%|▏         | 72.9M/4.98G [00:04<04:29, 18.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 74.0M/4.78G [00:04<03:55, 19.9MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 80.1M/4.93G [00:04<04:32, 17.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 75.8M/5.00G [00:04<03:56, 20.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 77.9M/4.93G [00:04<03:28, 23.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 75.0M/4.98G [00:04<04:28, 18.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 76.1M/4.78G [00:04<03:59, 19.7MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 82.3M/4.93G [00:04<04:31, 17.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 77.9M/5.00G [00:04<04:03, 20.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 77.8M/4.98G [00:04<03:55, 20.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 79.2M/4.78G [00:04<03:27, 22.7MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 85.4M/4.93G [00:04<03:54, 20.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 80.2M/4.93G [00:04<04:34, 17.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 92.3M/4.93G [00:04<02:33, 31.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 87.3M/4.93G [00:04<02:38, 30.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 80.0M/5.00G [00:04<05:10, 15.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 80.1M/4.98G [00:04<05:00, 16.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 83.3M/5.00G [00:04<04:08, 19.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 81.5M/4.78G [00:04<04:40, 16.7MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 96.0M/4.93G [00:04<02:39, 30.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 90.8M/4.93G [00:04<02:47, 28.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 82.1M/4.98G [00:04<04:41, 17.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 85.5M/5.00G [00:04<04:02, 20.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 83.7M/4.78G [00:04<04:21, 17.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 94.0M/4.93G [00:04<02:50, 28.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 84.8M/4.98G [00:04<04:08, 19.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 87.9M/5.00G [00:04<03:52, 21.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 86.3M/4.78G [00:04<03:56, 19.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 87.0M/4.98G [00:04<04:02, 20.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 90.1M/5.00G [00:04<03:53, 21.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 88.9M/4.78G [00:05<03:38, 21.5MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 99.4M/4.93G [00:04<03:51, 20.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 89.6M/4.98G [00:05<03:44, 21.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 91.2M/4.78G [00:05<03:40, 21.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 92.3M/5.00G [00:05<04:01, 20.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 102M/4.93G [00:05<03:42, 21.7MB/s] \u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 97.1M/4.93G [00:05<04:07, 19.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 91.9M/4.98G [00:05<03:57, 20.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 94.4M/5.00G [00:05<04:00, 20.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 93.5M/4.78G [00:05<03:49, 20.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 99.6M/4.93G [00:05<04:05, 19.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 105M/4.93G [00:05<03:54, 20.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 94.1M/4.98G [00:05<03:56, 20.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 95.6M/4.78G [00:05<03:48, 20.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 102M/4.93G [00:05<03:52, 20.8MB/s] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 108M/4.93G [00:05<03:20, 24.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 96.5M/5.00G [00:05<05:35, 14.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 96.2M/4.98G [00:05<05:12, 15.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 112M/4.93G [00:05<03:24, 23.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 102M/5.00G [00:05<03:35, 22.7MB/s] \u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 112M/4.93G [00:05<02:50, 28.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 101M/4.98G [00:05<03:38, 22.4MB/s] \u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 116M/4.93G [00:05<02:51, 28.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 97.7M/4.78G [00:05<06:10, 12.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 105M/5.00G [00:05<03:48, 21.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 103M/4.98G [00:05<03:39, 22.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 115M/4.93G [00:05<03:04, 26.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 99.9M/4.78G [00:05<05:24, 14.4MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 120M/4.93G [00:05<03:10, 25.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 107M/5.00G [00:05<03:48, 21.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 106M/4.98G [00:05<03:40, 22.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 102M/4.78G [00:05<05:01, 15.5MB/s] \u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 117M/4.93G [00:05<03:15, 24.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   2%|▏         | 122M/4.93G [00:05<03:17, 24.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 109M/5.00G [00:05<03:54, 20.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 104M/4.78G [00:05<04:48, 16.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 108M/4.98G [00:05<03:49, 21.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 120M/4.93G [00:05<03:26, 23.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 125M/4.93G [00:06<03:24, 23.5MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 106M/4.78G [00:06<04:38, 16.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 112M/5.00G [00:06<04:11, 19.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 110M/4.98G [00:06<03:54, 20.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   2%|▏         | 122M/4.93G [00:06<03:47, 21.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 127M/4.93G [00:06<03:27, 23.2MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 108M/4.78G [00:06<04:19, 18.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 114M/5.00G [00:06<04:52, 16.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 112M/4.78G [00:06<03:25, 22.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 113M/4.98G [00:06<05:13, 15.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 121M/5.00G [00:06<02:46, 29.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 130M/4.93G [00:06<04:32, 17.6MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 115M/4.78G [00:06<03:09, 24.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 115M/4.98G [00:06<04:26, 18.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   2%|▏         | 124M/5.00G [00:06<02:47, 29.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 133M/4.93G [00:06<04:02, 19.8MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   2%|▏         | 119M/4.78G [00:06<02:45, 28.1MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 118M/4.98G [00:06<03:56, 20.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 135M/4.93G [00:06<03:40, 21.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 127M/5.00G [00:06<02:51, 28.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 122M/4.78G [00:06<02:42, 28.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   2%|▏         | 121M/4.98G [00:06<03:32, 22.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 139M/4.93G [00:06<03:04, 26.0MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 126M/4.78G [00:06<02:21, 32.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 127M/4.98G [00:06<02:32, 31.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 130M/5.00G [00:06<03:16, 24.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 128M/4.93G [00:06<06:01, 13.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 143M/5.00G [00:06<01:40, 48.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 144M/4.93G [00:06<03:05, 25.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 133M/4.93G [00:06<04:20, 18.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 130M/4.78G [00:06<03:13, 24.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 130M/4.98G [00:06<03:28, 23.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 136M/4.93G [00:06<04:02, 19.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 147M/4.93G [00:06<03:21, 23.8MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 132M/4.78G [00:07<03:17, 23.5MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 149M/4.93G [00:07<03:31, 22.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 133M/4.98G [00:07<03:46, 21.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 139M/4.93G [00:07<04:12, 19.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 135M/4.78G [00:07<03:30, 22.1MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 152M/4.93G [00:07<03:35, 22.1MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 136M/4.98G [00:07<03:45, 21.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 148M/5.00G [00:07<02:54, 27.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 141M/4.93G [00:07<04:09, 19.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 137M/4.78G [00:07<03:32, 21.9MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 154M/4.93G [00:07<03:40, 21.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 138M/4.98G [00:07<03:44, 21.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 144M/4.93G [00:07<04:11, 19.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 140M/4.78G [00:07<03:39, 21.1MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 156M/4.93G [00:07<03:41, 21.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 141M/4.98G [00:07<03:41, 21.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 153M/5.00G [00:07<03:05, 26.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 142M/4.78G [00:07<03:26, 22.5MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 158M/4.93G [00:07<03:42, 21.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 143M/4.98G [00:07<03:34, 22.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 146M/4.93G [00:07<05:03, 15.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 156M/5.00G [00:07<03:12, 25.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 145M/4.98G [00:07<04:01, 20.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 145M/4.78G [00:07<04:32, 17.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 160M/5.00G [00:07<03:08, 25.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 160M/4.93G [00:07<05:02, 15.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 153M/4.98G [00:07<02:25, 33.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 148M/4.78G [00:07<03:47, 20.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 163M/5.00G [00:07<03:04, 26.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 163M/4.93G [00:07<04:18, 18.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 160M/4.93G [00:07<02:42, 29.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 150M/4.78G [00:07<03:35, 21.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 156M/4.98G [00:07<02:38, 30.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 165M/4.93G [00:07<04:16, 18.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 166M/5.00G [00:08<03:14, 24.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 163M/4.93G [00:07<02:55, 27.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 153M/4.78G [00:08<03:41, 20.9MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 167M/4.93G [00:08<04:18, 18.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 160M/4.98G [00:08<02:57, 27.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 169M/5.00G [00:08<03:25, 23.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 155M/4.78G [00:08<03:36, 21.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 165M/4.93G [00:08<03:03, 25.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 169M/4.93G [00:08<04:08, 19.2MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 172M/5.00G [00:08<03:16, 24.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 158M/4.78G [00:08<03:14, 23.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 168M/4.93G [00:08<02:58, 26.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   3%|▎         | 172M/4.93G [00:08<03:49, 20.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   3%|▎         | 171M/4.93G [00:08<02:59, 26.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   3%|▎         | 174M/5.00G [00:08<03:23, 23.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▎         | 174M/4.93G [00:08<03:36, 22.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 163M/4.98G [00:08<04:18, 18.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▎         | 175M/4.93G [00:08<02:37, 30.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   3%|▎         | 160M/4.78G [00:08<04:29, 17.1MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   3%|▎         | 173M/4.98G [00:08<02:20, 34.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▎         | 177M/5.00G [00:08<04:20, 18.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▎         | 174M/4.78G [00:08<01:47, 42.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▎         | 178M/4.93G [00:08<03:07, 25.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▎         | 184M/5.00G [00:08<02:39, 30.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 185M/4.93G [00:08<02:10, 36.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▎         | 178M/4.98G [00:08<02:44, 29.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 188M/5.00G [00:08<02:35, 30.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 179M/4.78G [00:08<02:07, 35.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 189M/4.93G [00:08<02:15, 34.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▎         | 182M/4.98G [00:08<02:41, 29.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 191M/5.00G [00:08<02:35, 30.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 184M/4.78G [00:08<02:07, 36.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 187M/4.98G [00:08<02:17, 34.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 192M/4.78G [00:09<01:52, 40.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 195M/5.00G [00:09<03:08, 25.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 193M/4.93G [00:09<03:10, 24.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 192M/4.98G [00:09<02:32, 31.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 198M/5.00G [00:09<03:05, 25.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 196M/4.93G [00:09<03:06, 25.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 197M/4.78G [00:09<02:04, 36.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 196M/4.98G [00:09<02:43, 29.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 200M/5.00G [00:09<03:13, 24.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 199M/4.93G [00:09<03:05, 25.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 201M/4.78G [00:09<02:15, 33.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 203M/5.00G [00:09<03:12, 25.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 202M/4.93G [00:09<03:05, 25.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 199M/4.98G [00:09<02:56, 27.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▎         | 177M/4.93G [00:09<14:01, 5.65MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 204M/4.78G [00:09<02:41, 28.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 206M/5.00G [00:09<03:41, 21.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 205M/4.93G [00:09<03:28, 22.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▎         | 178M/4.93G [00:09<12:05, 6.55MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 202M/4.98G [00:09<03:38, 21.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▎         | 180M/4.93G [00:09<10:13, 7.74MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 207M/4.93G [00:09<03:42, 21.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 207M/4.78G [00:09<03:07, 24.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 205M/4.98G [00:09<03:41, 21.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▎         | 183M/4.93G [00:09<07:13, 11.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 208M/5.00G [00:09<05:11, 15.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 190M/4.93G [00:09<03:40, 21.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 209M/4.93G [00:09<04:32, 17.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 211M/5.00G [00:09<04:18, 18.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 208M/4.98G [00:09<03:58, 20.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 210M/4.78G [00:10<03:55, 19.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 211M/4.93G [00:10<04:31, 17.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 210M/4.98G [00:10<03:57, 20.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 214M/5.00G [00:10<04:30, 17.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 212M/4.78G [00:10<03:51, 19.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 214M/4.93G [00:10<04:09, 18.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 216M/5.00G [00:10<04:09, 19.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 212M/4.98G [00:10<04:06, 19.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   4%|▍         | 214M/4.78G [00:10<03:52, 19.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 216M/4.93G [00:10<03:58, 19.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 218M/5.00G [00:10<04:04, 19.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 214M/4.98G [00:10<04:06, 19.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 216M/4.78G [00:10<03:59, 19.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 218M/4.93G [00:10<03:45, 20.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 220M/5.00G [00:10<04:10, 19.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   4%|▍         | 220M/4.93G [00:10<03:50, 20.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 218M/4.78G [00:10<04:07, 18.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 216M/4.98G [00:10<04:32, 17.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 194M/4.93G [00:10<06:23, 12.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 223M/4.93G [00:10<03:54, 20.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 222M/5.00G [00:10<04:45, 16.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 220M/4.78G [00:10<04:44, 16.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 218M/4.98G [00:10<05:21, 14.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 197M/4.93G [00:10<06:07, 12.9MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 222M/4.78G [00:10<04:25, 17.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 220M/4.98G [00:10<05:08, 15.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 200M/4.93G [00:10<05:17, 14.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 225M/4.93G [00:10<05:23, 14.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   4%|▍         | 224M/5.00G [00:10<06:14, 12.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 222M/4.98G [00:10<04:55, 16.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 227M/4.93G [00:10<05:01, 15.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 202M/4.93G [00:10<05:01, 15.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 226M/5.00G [00:10<05:53, 13.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 224M/4.78G [00:11<05:35, 13.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   4%|▍         | 223M/4.98G [00:10<05:06, 15.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 228M/4.93G [00:11<05:07, 15.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 228M/5.00G [00:11<05:33, 14.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 226M/4.78G [00:11<05:22, 14.1MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 204M/4.93G [00:11<04:57, 15.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 229M/5.00G [00:11<05:24, 14.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 227M/4.78G [00:11<05:39, 13.4MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 206M/4.93G [00:11<04:42, 16.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 230M/4.93G [00:11<06:11, 12.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 225M/4.98G [00:11<07:35, 10.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 231M/5.00G [00:11<06:20, 12.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 229M/4.78G [00:11<06:48, 11.1MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 226M/4.98G [00:11<07:27, 10.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 231M/4.93G [00:11<06:56, 11.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 232M/5.00G [00:11<06:27, 12.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 209M/4.93G [00:11<06:16, 12.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 227M/4.98G [00:11<07:23, 10.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 230M/4.78G [00:11<07:26, 10.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 233M/4.93G [00:11<07:31, 10.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 233M/5.00G [00:11<06:51, 11.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 229M/4.98G [00:11<07:21, 10.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 210M/4.93G [00:11<06:23, 12.3MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 231M/4.78G [00:11<08:04, 9.38MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 234M/4.93G [00:11<07:50, 9.99MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 235M/5.00G [00:11<07:01, 11.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 230M/4.98G [00:11<06:52, 11.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 212M/4.93G [00:11<06:02, 13.0MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 233M/4.78G [00:11<06:58, 10.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 236M/5.00G [00:11<06:22, 12.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 235M/4.93G [00:11<07:48, 10.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 232M/4.98G [00:11<06:17, 12.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 214M/4.93G [00:11<05:35, 14.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 234M/4.78G [00:11<06:34, 11.5MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 238M/5.00G [00:11<05:53, 13.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 236M/4.93G [00:11<07:27, 10.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 233M/4.98G [00:11<05:40, 13.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 215M/4.93G [00:11<05:30, 14.3MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 236M/4.78G [00:12<05:55, 12.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 240M/5.00G [00:12<05:16, 15.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 237M/4.93G [00:11<07:06, 11.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 235M/4.98G [00:12<05:20, 14.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 217M/4.93G [00:12<05:11, 15.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▍         | 238M/4.78G [00:12<05:04, 14.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 239M/4.93G [00:12<06:30, 12.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 238M/4.98G [00:12<04:19, 18.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   4%|▍         | 220M/4.93G [00:12<04:19, 18.2MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 240M/4.78G [00:12<04:40, 16.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▍         | 241M/5.00G [00:12<06:44, 11.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 240M/4.93G [00:12<07:51, 9.94MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▌         | 255M/5.00G [00:12<01:56, 40.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 241M/4.78G [00:12<05:16, 14.3MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 224M/4.93G [00:12<04:05, 19.2MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▍         | 243M/4.93G [00:12<05:16, 14.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 246M/4.78G [00:12<03:21, 22.5MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 228M/4.93G [00:12<03:08, 24.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 247M/4.93G [00:12<03:44, 20.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 250M/4.78G [00:12<02:40, 28.2MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 234M/4.93G [00:12<02:29, 31.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 240M/4.98G [00:12<08:21, 9.44MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 250M/4.93G [00:12<03:19, 23.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 242M/4.98G [00:12<06:41, 11.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 253M/4.78G [00:12<03:03, 24.6MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 237M/4.93G [00:12<02:46, 28.1MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 253M/4.93G [00:12<03:26, 22.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▌         | 260M/5.00G [00:12<03:18, 23.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 244M/4.98G [00:12<05:55, 13.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 255M/4.93G [00:12<03:29, 22.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 240M/4.93G [00:12<03:00, 26.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▌         | 264M/5.00G [00:12<03:11, 24.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 256M/4.78G [00:12<03:35, 21.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▍         | 247M/4.98G [00:12<04:54, 16.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▌         | 268M/5.00G [00:12<02:49, 28.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   5%|▌         | 260M/4.78G [00:13<02:53, 26.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 251M/4.98G [00:12<03:45, 20.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 257M/4.93G [00:13<04:33, 17.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 243M/4.93G [00:13<03:59, 19.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 253M/4.98G [00:13<03:47, 20.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 263M/4.78G [00:13<03:05, 24.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 259M/4.93G [00:13<04:16, 18.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▌         | 272M/5.00G [00:13<03:05, 25.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▍         | 245M/4.93G [00:13<03:54, 20.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 256M/4.98G [00:13<03:41, 21.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 266M/4.78G [00:13<03:10, 23.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 262M/4.93G [00:13<03:59, 19.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▌         | 249M/4.93G [00:13<03:12, 24.3MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 269M/4.78G [00:13<02:57, 25.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 265M/4.93G [00:13<03:30, 22.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 258M/4.98G [00:13<04:19, 18.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▌         | 252M/4.93G [00:13<03:20, 23.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   5%|▌         | 275M/5.00G [00:13<04:04, 19.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 267M/4.93G [00:13<03:34, 21.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 272M/4.78G [00:13<03:13, 23.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 260M/4.98G [00:13<04:20, 18.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▌         | 254M/4.93G [00:13<03:24, 22.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   5%|▌         | 270M/4.93G [00:13<03:23, 22.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 277M/5.00G [00:13<03:56, 19.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 263M/4.98G [00:13<03:41, 21.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 283M/5.00G [00:13<02:54, 27.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   5%|▌         | 272M/4.98G [00:13<02:01, 38.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▌         | 257M/4.93G [00:13<03:53, 20.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 272M/4.93G [00:13<04:21, 17.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   5%|▌         | 271M/4.93G [00:13<01:35, 48.7MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 274M/4.78G [00:13<05:19, 14.1MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 281M/4.93G [00:13<02:19, 33.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 276M/4.98G [00:13<02:43, 28.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 279M/4.78G [00:14<03:34, 21.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 288M/5.00G [00:13<03:30, 22.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 285M/4.93G [00:13<02:06, 36.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 291M/5.00G [00:14<03:27, 22.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 282M/4.78G [00:14<03:32, 21.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 280M/4.98G [00:14<02:54, 26.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 277M/4.93G [00:14<02:18, 33.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 294M/5.00G [00:14<03:14, 24.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 285M/4.78G [00:14<03:15, 23.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 283M/4.98G [00:14<02:57, 26.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 289M/4.93G [00:14<03:01, 25.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 281M/4.93G [00:14<02:28, 31.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 297M/5.00G [00:14<03:22, 23.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 286M/4.98G [00:14<03:00, 26.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|��         | 293M/4.93G [00:14<02:55, 26.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 301M/5.00G [00:14<02:54, 26.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 288M/4.78G [00:14<04:06, 18.2MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 285M/4.93G [00:14<02:29, 31.1MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 296M/4.93G [00:14<02:49, 27.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 291M/4.78G [00:14<03:42, 20.1MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 304M/5.00G [00:14<02:55, 26.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 289M/4.98G [00:14<03:38, 21.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 299M/4.93G [00:14<02:41, 28.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 295M/4.78G [00:14<03:05, 24.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 294M/4.98G [00:14<02:51, 27.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 303M/4.93G [00:14<02:24, 32.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 289M/4.93G [00:14<03:17, 23.5MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▌         | 298M/4.78G [00:14<03:07, 23.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 307M/5.00G [00:14<03:51, 20.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 297M/4.98G [00:14<02:56, 26.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 292M/4.93G [00:14<03:08, 24.6MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▋         | 301M/4.78G [00:14<02:56, 25.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 309M/5.00G [00:14<03:35, 21.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 300M/4.98G [00:14<02:55, 26.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 295M/4.93G [00:14<03:01, 25.5MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▋         | 304M/4.78G [00:15<02:49, 26.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▌         | 312M/5.00G [00:14<03:18, 23.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 303M/4.98G [00:14<02:45, 28.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 300M/4.93G [00:15<02:36, 29.5MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   6%|▋         | 306M/4.78G [00:15<03:05, 24.1MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▋         | 320M/5.00G [00:15<02:26, 31.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 306M/4.98G [00:15<03:13, 24.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 315M/4.78G [00:15<01:49, 40.7MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 304M/4.93G [00:15<02:48, 27.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   6%|▋         | 323M/5.00G [00:15<02:32, 30.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▌         | 309M/4.98G [00:15<03:02, 25.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▌         | 307M/4.93G [00:15<02:47, 27.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 326M/5.00G [00:15<02:34, 30.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 320M/4.78G [00:15<02:04, 35.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▋         | 312M/4.98G [00:15<02:55, 26.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▋         | 310M/4.93G [00:15<02:40, 28.8MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 330M/5.00G [00:15<02:30, 31.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▋         | 315M/4.98G [00:15<02:52, 27.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▌         | 307M/4.93G [00:15<07:09, 10.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▋         | 313M/4.93G [00:15<03:00, 25.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▋         | 318M/4.98G [00:15<03:09, 24.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 333M/5.00G [00:15<02:53, 26.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 324M/4.78G [00:15<02:56, 25.3MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▋         | 310M/4.93G [00:15<06:28, 11.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▋         | 316M/4.93G [00:15<03:19, 23.1MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 336M/5.00G [00:15<03:06, 25.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 327M/4.78G [00:15<02:59, 24.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▋         | 312M/4.93G [00:15<05:40, 13.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   6%|▋         | 319M/4.93G [00:15<03:08, 24.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▋         | 320M/4.98G [00:15<04:31, 17.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 331M/4.78G [00:15<02:40, 27.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▋         | 316M/4.93G [00:15<04:31, 17.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 338M/5.00G [00:15<03:58, 19.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   6%|▋         | 322M/4.98G [00:15<04:19, 17.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   6%|▋         | 318M/4.93G [00:15<04:15, 18.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 334M/4.78G [00:16<02:50, 26.1MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 322M/4.93G [00:16<04:05, 18.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 324M/4.98G [00:16<04:14, 18.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 340M/5.00G [00:16<04:20, 17.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 324M/4.93G [00:16<03:55, 19.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 328M/4.98G [00:16<03:29, 22.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 344M/5.00G [00:16<03:24, 22.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 327M/4.93G [00:16<03:20, 23.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 331M/4.98G [00:16<03:14, 23.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 321M/4.93G [00:16<05:20, 14.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 337M/4.78G [00:16<04:06, 18.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 347M/5.00G [00:16<03:46, 20.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 330M/4.93G [00:16<03:30, 21.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 323M/4.93G [00:16<05:11, 14.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 333M/4.98G [00:16<03:35, 21.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 339M/4.78G [00:16<04:12, 17.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 349M/5.00G [00:16<03:51, 20.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 325M/4.93G [00:16<04:57, 15.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 332M/4.93G [00:16<03:46, 20.3MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 336M/4.98G [00:16<03:44, 20.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 341M/4.78G [00:16<04:08, 17.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 351M/5.00G [00:16<03:55, 19.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 327M/4.93G [00:16<04:32, 16.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 335M/4.93G [00:16<03:39, 20.9MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 344M/4.78G [00:16<03:33, 20.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 331M/4.93G [00:16<03:18, 23.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 338M/4.98G [00:16<04:20, 17.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 348M/4.78G [00:16<03:07, 23.7MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 337M/4.93G [00:16<04:27, 17.2MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 340M/4.98G [00:16<04:02, 19.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 334M/4.93G [00:16<03:23, 22.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 353M/5.00G [00:16<05:12, 14.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 339M/4.93G [00:16<04:24, 17.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 342M/4.98G [00:16<04:07, 18.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 350M/4.78G [00:17<03:25, 21.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 355M/5.00G [00:16<05:11, 14.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 341M/4.93G [00:17<03:54, 19.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 345M/4.98G [00:17<03:38, 21.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 359M/5.00G [00:17<03:51, 20.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 346M/4.93G [00:17<03:00, 25.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 348M/4.98G [00:17<03:10, 24.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 353M/4.78G [00:17<04:08, 17.8MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 362M/5.00G [00:17<03:24, 22.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 337M/4.93G [00:17<05:41, 13.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 355M/4.78G [00:17<03:56, 18.7MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 351M/4.98G [00:17<03:16, 23.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 348M/4.93G [00:17<03:13, 23.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 365M/5.00G [00:17<03:37, 21.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 339M/4.93G [00:17<05:09, 14.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   7%|▋         | 357M/4.78G [00:17<03:52, 19.0MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 351M/4.93G [00:17<03:15, 23.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 367M/5.00G [00:17<03:34, 21.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 342M/4.93G [00:17<04:17, 17.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 360M/4.78G [00:17<03:26, 21.4MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 353M/4.98G [00:17<04:12, 18.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 345M/4.93G [00:17<03:34, 21.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 364M/4.78G [00:17<02:50, 25.9MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 357M/4.98G [00:17<03:24, 22.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 353M/4.93G [00:17<04:19, 17.7MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 369M/5.00G [00:17<04:30, 17.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 348M/4.93G [00:17<03:42, 20.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 360M/4.98G [00:17<03:33, 21.7MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 355M/4.93G [00:17<04:12, 18.1MB/s]\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 367M/4.78G [00:17<03:11, 23.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 371M/5.00G [00:17<04:19, 17.8MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 351M/4.93G [00:17<03:30, 21.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 362M/4.98G [00:17<03:23, 22.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 358M/4.93G [00:17<03:58, 19.2MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   7%|▋         | 374M/5.00G [00:17<03:54, 19.7MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 369M/4.78G [00:17<03:38, 20.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 364M/4.98G [00:17<03:20, 22.9MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 360M/4.93G [00:17<03:41, 20.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 376M/5.00G [00:17<03:36, 21.4MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 372M/4.78G [00:18<03:20, 22.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 367M/4.98G [00:17<03:19, 23.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 363M/4.93G [00:18<03:28, 21.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 379M/5.00G [00:18<03:29, 22.1MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 353M/4.93G [00:17<04:36, 16.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 374M/4.78G [00:18<03:28, 21.1MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 365M/4.93G [00:18<03:28, 21.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 381M/5.00G [00:18<03:21, 22.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 355M/4.93G [00:18<04:19, 17.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 377M/4.78G [00:18<03:32, 20.7MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 367M/4.93G [00:18<03:31, 21.5MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 358M/4.93G [00:18<03:59, 19.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 369M/4.98G [00:18<04:28, 17.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 384M/5.00G [00:18<03:37, 21.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 379M/4.78G [00:18<03:23, 21.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 361M/4.93G [00:18<03:14, 23.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   7%|▋         | 372M/4.98G [00:18<03:49, 20.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 382M/4.78G [00:18<03:09, 23.2MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 364M/4.93G [00:18<03:05, 24.6MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 375M/4.98G [00:18<03:36, 21.2MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 386M/5.00G [00:18<04:28, 17.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   7%|▋         | 369M/4.93G [00:18<05:13, 14.6MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 388M/5.00G [00:18<04:17, 17.9MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 367M/4.93G [00:18<03:14, 23.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 377M/4.98G [00:18<03:45, 20.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   8%|▊         | 372M/4.93G [00:18<04:37, 16.4MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 392M/5.00G [00:18<03:26, 22.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 381M/4.98G [00:18<03:03, 25.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 384M/4.78G [00:18<04:34, 16.0MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   8%|▊         | 375M/4.93G [00:18<03:45, 20.2MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   7%|▋         | 369M/4.93G [00:18<03:56, 19.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 394M/5.00G [00:18<03:39, 21.0MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 386M/4.78G [00:18<04:25, 16.6MB/s]\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   8%|▊         | 377M/4.93G [00:18<03:47, 20.0MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 384M/4.98G [00:18<03:30, 21.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   8%|▊         | 371M/4.93G [00:18<03:56, 19.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 388M/4.78G [00:18<04:17, 17.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 396M/5.00G [00:18<03:43, 20.6MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   8%|▊         | 380M/4.93G [00:18<03:37, 20.9MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   8%|▊         | 374M/4.93G [00:18<03:32, 21.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 391M/4.78G [00:19<03:43, 19.6MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 399M/5.00G [00:18<03:24, 22.5MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "model-00003-of-00007.safetensors:   8%|▊         | 382M/4.93G [00:19<03:35, 21.1MB/s]\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   8%|▊         | 376M/4.93G [00:19<03:32, 21.4MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 386M/4.98G [00:19<04:41, 16.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 393M/4.78G [00:19<03:39, 20.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   8%|▊         | 380M/4.93G [00:19<02:51, 26.5MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 390M/4.98G [00:19<03:49, 20.0MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 396M/4.78G [00:19<03:19, 22.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 401M/5.00G [00:19<04:27, 17.2MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   8%|▊         | 383M/4.93G [00:19<02:49, 26.8MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00001-of-00007.safetensors:   8%|▊         | 392M/4.98G [00:19<03:35, 21.3MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 398M/4.78G [00:19<03:10, 23.0MB/s]\u001b[A\n",
-      "\n",
-      "\n",
-      "model-00005-of-00007.safetensors:   8%|▊         | 404M/5.00G [00:19<03:45, 20.3MB/s]\u001b[A\u001b[A\u001b[A\n",
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "model-00004-of-00007.safetensors:   8%|▊         | 386M/4.93G [00:19<03:08, 24.1MB/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
-      "model-00002-of-00007.safetensors:   8%|▊         | 401M/4.78G [00:19<03:34, 20.4MB/s]\u001b[A"
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[0;32m/tmp/ipykernel_9719/2177510705.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"neginashz/checkpoint-162\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"neginashz/checkpoint-162\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36mpush_to_hub\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   3085\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3086\u001b[0m             \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"tags\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3087\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3088\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3089\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget_memory_footprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreturn_buffers\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/utils/hub.py\u001b[0m in \u001b[0;36mpush_to_hub\u001b[0;34m(self, repo_id, use_temp_dir, commit_message, private, token, max_shard_size, create_pr, safe_serialization, revision, commit_description, tags, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m    947\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    948\u001b[0m             \u001b[0;31m# Save all files.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 949\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwork_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_shard_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax_shard_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msafe_serialization\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msafe_serialization\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    950\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    951\u001b[0m             \u001b[0;31m# Update model card if needed:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36msave_pretrained\u001b[0;34m(self, save_directory, is_main_process, state_dict, save_function, push_to_hub, max_shard_size, safe_serialization, variant, token, save_peft_format, **kwargs)\u001b[0m\n\u001b[1;32m   3032\u001b[0m                 \u001b[0;31m# At some point we will need to deal better with save_function (used for TPU and other distributed\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3033\u001b[0m                 \u001b[0;31m# joyfulness), but for now this enough.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3034\u001b[0;31m                 \u001b[0msafe_save_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mshard\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_directory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshard_file\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m\"format\"\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m\"pt\"\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3035\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3036\u001b[0m                 \u001b[0msave_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mshard\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_directory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshard_file\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/.local/lib/python3.10/site-packages/safetensors/torch.py\u001b[0m in \u001b[0;36msave_file\u001b[0;34m(tensors, filename, metadata)\u001b[0m\n\u001b[1;32m    284\u001b[0m     \u001b[0;31m`\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    285\u001b[0m     \"\"\"\n\u001b[0;32m--> 286\u001b[0;31m     \u001b[0mserialize_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_flatten\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensors\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    288\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
    ],
    "source": [
-    "model.push_to_hub(\"neginashz/checkpoint-80\")\n",
-    "tokenizer.push_to_hub(\"neginashz/checkpoint-80\")\n"
+    "model.push_to_hub(\"neginashz/checkpoint-162\")\n",
+    "tokenizer.push_to_hub(\"neginashz/checkpoint-162\")\n"
    ]
   }
  ],