mirror of
https://github.com/trholding/llama2.c.git
synced 2026-02-06 11:26:53 +00:00
131 lines
3.9 KiB
Plaintext
131 lines
3.9 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "HLdoj4cz-xal"
|
|
},
|
|
"source": [
|
|
"# Run.c\n",
|
|
"\n",
|
|
"[](https://colab.research.google.com/github/karpathy/llama2.c/blob/master/run.ipynb)\n",
|
|
"\n",
|
|
"More details can be found in the [README.md](README.md) ."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "Une3Ozlnu1B7"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#@title Clone Project\n",
|
|
"\n",
|
|
"!git clone https://github.com/karpathy/llama2.c.git\n",
|
|
"%cd llama2.c"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#@title Build\n",
|
|
"\n",
|
|
"!make runfast"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "thm0ZBrtSgoC"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#@title Pick Your Model\n",
|
|
"\n",
|
|
"#@markdown Choose model\n",
|
|
"model = \"stories15M\" #@param [\"stories15M\", \"stories42M\", \"stories110M\"]\n",
|
|
"\n",
|
|
"download_url = \"\"\n",
|
|
"\n",
|
|
"if(model == \"stories15M\"):\n",
|
|
" download_url = \"https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.bin\"\n",
|
|
"if(model == \"stories42M\"):\n",
|
|
" download_url = \"https://huggingface.co/karpathy/tinyllamas/resolve/main/stories42M.bin\"\n",
|
|
"if(model == \"stories110M\"):\n",
|
|
" download_url = \"https://huggingface.co/karpathy/tinyllamas/resolve/main/stories110M.bin\"\n",
|
|
"\n",
|
|
"print(f\"download_url: {download_url}\")\n",
|
|
"\n",
|
|
"!wget $download_url\n",
|
|
"\n",
|
|
"model_file = model + \".bin\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "OgAc3KjuT-NM"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"#@title Generate Stories\n",
|
|
"\n",
|
|
"# Generate args\n",
|
|
"max_token = 256 #@param {type:\"slider\", min:32, max:1024, step:32}\n",
|
|
"temperature = 0.8 #@param {type:\"slider\", min:0.0, max:1, step:0.05}\n",
|
|
"top_p = 0.9 #@param {type:\"slider\", min:0.0, max:1.0, step:0.05}\n",
|
|
"prompt = \"One day, Lily met a Shoggoth\" #@param {type:\"string\"}\n",
|
|
"\n",
|
|
"print(f\"model: {model_file}, max_token: {max_token}, temperature: {temperature}, top_p: {top_p}, prompt: {prompt}\")\n",
|
|
"print(f\"----------------------------\\n\")\n",
|
|
"\n",
|
|
"cmd = f'./run {model_file} -t {temperature} -p {top_p} -n {max_token} -i \"{prompt}\"'\n",
|
|
"!{cmd}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#@title Run Meta's Llama 2 models\n",
|
|
"\n",
|
|
"#@markdown input your huggingface [access token](https://huggingface.co/settings/tokens) to download Meta's Llama 2 models.\n",
|
|
"\n",
|
|
"from huggingface_hub import snapshot_download\n",
|
|
"\n",
|
|
"token = \"replace your huggingface access token\" #@param {type:\"string\"}\n",
|
|
"path = snapshot_download(repo_id=\"meta-llama/Llama-2-7b\",cache_dir=\"Llama-2-7b\", use_auth_token=token)\n",
|
|
"\n",
|
|
"!python export_meta_llama_bin.py $path llama2_7b.bin\n",
|
|
"\n",
|
|
"print(\"./run llama2_7b.bin\\n\")\n",
|
|
"!./run llama2_7b.bin"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"private_outputs": true,
|
|
"provenance": []
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"name": "python"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0
|
|
}
|