Updated Llama 2 to 3 paths (#413)

* llama 2 and 3 path fixes

* updated llama 3, 3.1 and 3.2 paths

* updated .gitignore

* Typo fix

---------

Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>

.gitignore

@@ -35,12 +35,15 @@ ch05/01_main-chapter-code/model.pth
 ch05/01_main-chapter-code/model_and_optimizer.pth
 ch05/03_bonus_pretraining_on_gutenberg/model_checkpoints
 ch05/06_user_interface/gpt2
+ch05/07_gpt_to_llama/.cache
 ch05/07_gpt_to_llama/Llama-2-7b
 ch05/07_gpt_to_llama/Llama-2-7b-chat
-ch05/07_gpt_to_llama/.cache
+ch05/07_gpt_to_llama/Llama-3-8B
-ch05/07_gpt_to_llama/llama3-files
+ch05/07_gpt_to_llama/Llama-3-8B-Instruct
-ch05/07_gpt_to_llama/llama31-files
+ch05/07_gpt_to_llama/Llama-3.1-8B
-ch05/07_gpt_to_llama/llama32-files
+ch05/07_gpt_to_llama/Llama-3.1-8B-Instruct
+ch05/07_gpt_to_llama/Llama-3.2-1B
+ch05/07_gpt_to_llama/Llama-3.2-1B-Instruct
 
 ch06/01_main-chapter-code/gpt2
 ch06/02_bonus_additional-experiments/gpt2

ch05/07_gpt_to_llama/converting-gpt-to-llama2.ipynb

@@ -1189,7 +1189,7 @@
     "tokenizer_file = hf_hub_download(\n",
     "    repo_id=\"meta-llama/Llama-2-7b\",\n",
     "    filename=\"tokenizer.model\",\n",
-    "    local_dir=\"Llama-2-7B\"\n",
+    "    local_dir=\"Llama-2-7b\"\n",
     ")"
    ]
   },

ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb

@@ -1252,7 +1252,7 @@
     "tokenizer_file_path = hf_hub_download(\n",
     "    repo_id=\"meta-llama/Meta-Llama-3-8B\",\n",
     "    filename=\"original/tokenizer.model\",\n",
-    "    local_dir=\"llama3-files\"\n",
+    "    local_dir=\"Llama-3-8B\"\n",
     ")"
    ]
   },
@@ -1458,7 +1458,7 @@
     "    weights_file = hf_hub_download(\n",
     "        repo_id=\"meta-llama/Meta-Llama-3-8B\",\n",
     "        filename=f\"model-0000{i}-of-00004.safetensors\",\n",
-    "        local_dir=\"llama3-files\"\n",
+    "        local_dir=\"Llama-3-8B\"\n",
     "    )\n",
     "    current_weights = load_file(weights_file)\n",
     "    combined_weights.update(current_weights)"
@@ -1677,7 +1677,7 @@
     "id": "akyo7WNyF_YL"
    },
    "source": [
-    "- Above, we used the pretrained base model; if you want to use a model capable of following instructions, use the `\"meta-llama/Llama-3-8b-Instruct\"` model instead, as shown below"
+    "- Above, we used the pretrained base model; if you want to use a model capable of following instructions, use the `\"meta-llama/Llama-3-8B-Instruct\"` model instead, as shown below"
    ]
   },
   {
@@ -1824,7 +1824,7 @@
     "    weights_file = hf_hub_download(\n",
     "        repo_id=\"meta-llama/Meta-Llama-3-8B-Instruct\",\n",
     "        filename=f\"model-0000{i}-of-00004.safetensors\",\n",
-    "        local_dir=\"llama3-files\"\n",
+    "        local_dir=\"Llama-3-8B-Instruct\"\n",
     "    )\n",
     "    current_weights = load_file(weights_file)\n",
     "    combined_weights.update(current_weights)\n",
@@ -2157,7 +2157,7 @@
     "tokenizer_file_path = hf_hub_download(\n",
     "    repo_id=\"meta-llama/Llama-3.1-8B\",\n",
     "    filename=\"original/tokenizer.model\",\n",
-    "    local_dir=\"llama31-files\"\n",
+    "    local_dir=\"Llama-3.1-8B\"\n",
     ")\n",
     "\n",
     "tokenizer = Tokenizer(tokenizer_file_path)"
@@ -2313,7 +2313,7 @@
     "    weights_file = hf_hub_download(\n",
     "        repo_id=\"meta-llama/Llama-3.1-8B\",\n",
     "        filename=f\"model-0000{i}-of-00004.safetensors\",\n",
-    "        local_dir=\"llama31-files\"\n",
+    "        local_dir=\"Llama-3.1-8B\"\n",
     "    )\n",
     "    current_weights = load_file(weights_file)\n",
     "    combined_weights.update(current_weights)\n",
@@ -2512,7 +2512,7 @@
     "tokenizer_file_path = hf_hub_download(\n",
     "    repo_id=\"meta-llama/Llama-3.2-1B\",\n",
     "    filename=\"original/tokenizer.model\",\n",
-    "    local_dir=\"llama32-files\"\n",
+    "    local_dir=\"Llama-3.2-1B\"\n",
     ")\n",
     "\n",
     "tokenizer = Tokenizer(tokenizer_file_path)"
@@ -2589,7 +2589,7 @@
     "weights_file = hf_hub_download(\n",
     "    repo_id=\"meta-llama/Llama-3.2-1B\",\n",
     "    filename=f\"model.safetensors\",\n",
-    "    local_dir=\"llama32-files\"\n",
+    "    local_dir=\"Llama-3.2-1B\"\n",
     ")\n",
     "current_weights = load_file(weights_file)\n",
     "\n",
@@ -2687,7 +2687,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "pt",
    "language": "python",
    "name": "python3"
   },
@@ -2701,7 +2701,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.9"
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {

ch05/07_gpt_to_llama/standalone-llama32.ipynb

@@ -733,7 +733,7 @@
     "tokenizer_file_path = hf_hub_download(\n",
     "    repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
     "    filename=\"original/tokenizer.model\",\n",
-    "    local_dir=\"llama32-files\"\n",
+    "    local_dir=\"Llama-3.2-1B-Instruct\"\n",
     ")"
    ]
   },
@@ -860,7 +860,7 @@
     "    weights_file = hf_hub_download(\n",
     "        repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
     "        filename=f\"model.safetensors\",\n",
-    "        local_dir=\"llama32-files\"\n",
+    "        local_dir=\"Llama-3.2-1B-Instruct\"\n",
     "    )\n",
     "    combined_weights = load_file(weights_file)\n",
     "\n",
@@ -871,7 +871,7 @@
     "        weights_file = hf_hub_download(\n",
     "            repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
     "            filename=f\"model-0000{i}-of-00002.safetensors\",\n",
-    "            local_dir=\"llama32-files\"\n",
+    "            local_dir=\"Llama-3.2-1B-Instruct\"\n",
     "        )\n",
     "        current_weights = load_file(weights_file)\n",
     "        combined_weights.update(current_weights)\n",
@@ -1047,7 +1047,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "pt",
    "language": "python",
    "name": "python3"
   },
@@ -1061,7 +1061,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,