Merge branch 'karpathy:master' into master

README.md

@@ -10,6 +10,8 @@ Please note that this started recently as just a fun weekend project: I took my
 
 ## feel the magic
 
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/karpathy/llama2.c/blob/master/run.ipynb)
+
 First, navigate to the folder when you keep your projects and clone this repository to this folder:
 
 ```bash
@@ -240,7 +242,9 @@ If your candidate PRs have elements of these it doesn't mean they won't get merg
 - Kotlin
   - [llama2.kt](https://github.com/madroidmaq/llama2.kt) by @[madroidmaq](https://github.com/madroidmaq): a Kotlin port of this project
 - Python
-  - [llama2.py](https://github.com/tairov/llama2.py) by @[tairov](https://github.com/tairov): a simple one file pure Python port of this project with zero dependencies 
+  - [llama2.py](https://github.com/tairov/llama2.py) by @[tairov](https://github.com/tairov): a simple one file pure Python port of this project with zero dependencies
+- C#
+  - [llama2.cs](https://github.com/trrahul/llama2.cs) by @[trrahul](https://github.com/trrahul): a C# port of this project
 - [llama2.c - Llama 2 Everywhere](https://github.com/trholding/llama2.c) by @[trholding](https://github.com/trholding): Standalone, Bootable & Portable Binary Llama 2
 
 ## unsorted todos

run.c

@@ -517,7 +517,7 @@ int main(int argc, char *argv[]) {
     char *checkpoint = NULL;  // e.g. out/model.bin
     float temperature = 1.0f; // 0.0 = greedy deterministic. 1.0 = original. don't set higher
     float topp = 0.9f;        // top-p in nucleus sampling
-    rng_seed = (unsigned int)time(NULL); // seed rng with time by default
+    rng_seed = 0; // seed rng with time by default
     int steps = 256;          // number of steps to run for
     char *prompt = NULL;      // prompt string
 
@@ -536,7 +536,7 @@ int main(int argc, char *argv[]) {
         else if (argv[i][1] == 'i') { prompt = argv[i + 1]; }
         else { error_usage(); }
     }
-    if(rng_seed == 0) { fprintf(stderr, "Cannot use seed=0 because of the rng alg used\n"); return 1; }
+    if(rng_seed == 0) { rng_seed =  (unsigned int)time(NULL);}
 
     // read in the model.bin file
     Config config;

run.ipynb

@@ -0,0 +1,109 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HLdoj4cz-xal"
+      },
+      "source": [
+        "# Run.c\n",
+        "\n",
+        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](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}"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "private_outputs": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}