yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-09-26 08:34:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated Llama 2 to 3 paths (#413)

Browse Source 
* 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>
This commit is contained in:
Daniel Kleine 2024-10-24 14:40:08 +02:00 committed by GitHub
parent 632d7772b2
commit 8b60460319
4 changed files with 23 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
.gitignore vendored
View File

@ -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/llama3-files
ch05/07_gpt_to_llama/llama31-files
ch05/07_gpt_to_llama/llama32-files
ch05/07_gpt_to_llama/Llama-3-8B
ch05/07_gpt_to_llama/Llama-3-8B-Instruct
ch05/07_gpt_to_llama/Llama-3.1-8B
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

2
ch05/07_gpt_to_llama/converting-gpt-to-llama2.ipynb
View File

@ -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",
")"
]
},

20
ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb
View File

@ -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": {

10
ch05/07_gpt_to_llama/standalone-llama32.ipynb
View File

@ -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,