Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tinystories.sentis filter=lfs diff=lfs merge=lfs -text

README (1).md

@@ -0,0 +1,43 @@
+---
+license: mit
+library_name: unity-sentis
+pipeline_tag: text-generation
+---
+
+# Tiny Stories Model in Unity Sentis Format (Sentis 1.4.0-pre.2*)
+*Version 1.3.0 Sentis files are not compatible with Sentis 1.4.0 and would need to be recreated/downloaded
+
+This is the [Tiny Stories model](https://huggingface.co/roneneldan/TinyStories-33M) checked to run on Unity 2023. Tiny Stories is a Large Language Model that was trained on children's stories and can create stories based on the first couple of sentences.
+
+
+## How to Use
+* Create a new scene in Unity 2023
+* Install `com.unity.sentis` and `com.unity.nuget.newtonsoft-json` packages
+* Add the RunTinyStories.cs file to the Main Camera
+* Put `tinystories.sentis`, `vocab.json` and `merges.txt` in the Assets/StreamingAssets folder
+* Adjust some of the variables such as the `outputText` string to set the prompt
+* Press run
+* The output will appear in the console window
+
+## Example Input
+```
+One day an alien came down from Mars. It saw a chicken
+```
+## Example Output
+```
+One day an alien came down from Mars. It saw a chicken and said, "Hello, little chicken. What are you doing here?"
+
+The chicken replied, "I'm looking for a place to stay. I'm very tired."
+
+The alien said, "You can stay here. I have a nice place for you. It's very comfortable."
+
+The chicken was so happy. She thanked the alien and said, "Thank you. I'm very comfortable here."
+
+The alien smiled and said, "You're welcome
+```
+
+## Unity Sentis
+Unity Sentis is the inference engine which runs on Unity 2023. More can be found about it [here](https://unity.com/products/sentis)
+
+## Disclaimer
+The model was trained on children's stories so very unlikely to produce undesirable text. As an extra precaution, we removed a few tokens from vocab.json that might not be suitable for younger audiences. The original json can be found on the Tiny Stories original page.

RunTinyStories.cs

@@ -0,0 +1,262 @@
+using System.Collections;
+using System.Collections.Generic;
+using UnityEngine;
+using Unity.Sentis;
+using System.IO;
+using System.Text;
+using FF = Unity.Sentis.Functional;
+
+/*
+ *              Tiny Stories Inference Code
+ *              ===========================
+ *  
+ *  Put this script on the Main Camera
+ *  
+ *  In Assets/StreamingAssets put:
+ *  
+ *  tinystories.sentis (or put in asset folder and drag onto field)
+ *  vocab.json
+ *  merges.txt
+ * 
+ *  Install package com.unity.nuget.newtonsoft-json from packagemanger
+ *  Install package com.unity.sentis
+ * 
+ */
+
+
+public class RunTinyStories : MonoBehaviour
+{
+    //Drop the tinystories.sentis or onnx file on here if using an asset:
+    //public ModelAsset asset;
+    const BackendType backend = BackendType.GPUCompute;
+
+    //string outputString = "Once upon a time, there were three bears";
+    string outputString = "One day an alien came down from Mars. It saw a chicken";
+
+    // This is how many tokens you want. It can be adjusted.
+    const int maxTokens = 100;
+
+    //Make this smaller for more randomness
+    const float predictability = 5f;
+
+    //Special tokens
+    const int END_OF_TEXT = 50256;
+
+    //Store the vocabulary
+    string[] tokens;
+
+    IWorker engine;
+
+    int currentToken = 0;
+    int[] outputTokens = new int[maxTokens];
+
+    // Used for special character decoding
+    int[] whiteSpaceCharacters = new int[256];
+    int[] encodedCharacters = new int[256];
+
+    bool runInference = false;
+
+
+    //stop after this many tokens
+    const int stopAfter = 100;
+
+    int totalTokens = 0;
+
+    string[] merges;
+    Dictionary<string, int> vocab;
+
+    void Start()
+    {
+        SetupWhiteSpaceShifts();
+
+        LoadVocabulary();
+
+        var model1 = ModelLoader.Load(Path.Join(Application.streamingAssetsPath , "tinystories.sentis"));
+        //var model1 = ModelLoader.Load(asset);
+        //Create a new model to select the random token:
+        var model2 = FF.Compile(
+            (input, currentToken) =>
+            {
+                var row = FF.Select(model1.Forward(input)[8], 1, currentToken);
+                return FF.Multinomial(predictability * row, 1);
+            },
+            (model1.inputs[0], InputDef.Int(new TensorShape()))
+        );
+
+        engine = WorkerFactory.CreateWorker(backend, model2);
+
+        DecodePrompt(outputString);
+
+        runInference = true;
+    }
+
+    // Update is called once per frame
+    void Update()
+    {
+        if (runInference)
+        {
+            RunInference();
+        }
+    }
+
+    void RunInference()
+    {
+        using var tokensSoFar = new TensorInt(new TensorShape(1, maxTokens), outputTokens);
+        using var index = new TensorInt(currentToken);
+
+        engine.Execute(new Dictionary<string, Tensor> { {"input_0", tokensSoFar },  { "input_1", index }});
+
+        var probs = engine.PeekOutput() as TensorInt;
+        Debug.Log(probs.shape);
+
+        probs.CompleteOperationsAndDownload();
+
+        int ID = probs[0];
+
+        //shift window down if got to the end
+        if (currentToken >= maxTokens - 1)
+        {
+            for (int i = 0; i < maxTokens - 1; i++) outputTokens[i] = outputTokens[i + 1];
+            currentToken--;
+        }
+
+        outputTokens[++currentToken] = ID;
+        totalTokens++;
+
+        if (ID == END_OF_TEXT || totalTokens >= stopAfter)
+        {
+            runInference = false;
+        }
+        else outputString += GetUnicodeText(tokens[ID]);
+
+        Debug.Log(outputString);
+
+    }
+
+    void DecodePrompt(string text)
+    {
+        var inputTokens = GetTokens(text);
+
+        for(int i = 0; i < inputTokens.Count; i++)
+        {
+            outputTokens[i] = inputTokens[i];
+        }
+        currentToken = inputTokens.Count - 1;
+    }
+   
+    void LoadVocabulary()
+    {
+        var jsonText = File.ReadAllText(Path.Join(Application.streamingAssetsPath , "vocab.json"));
+        vocab = Newtonsoft.Json.JsonConvert.DeserializeObject<Dictionary<string, int>>(jsonText);
+        tokens = new string[vocab.Count];
+        foreach (var item in vocab)
+        {
+            tokens[item.Value] = item.Key;
+        }
+
+        merges = File.ReadAllLines(Path.Join(Application.streamingAssetsPath , "merges.txt"));
+    }
+
+    // Translates encoded special characters to Unicode
+    string GetUnicodeText(string text)
+    {
+        var bytes = Encoding.GetEncoding("ISO-8859-1").GetBytes(ShiftCharacterDown(text));
+        return Encoding.UTF8.GetString(bytes);
+    }
+    string GetASCIIText(string newText)
+    {
+        var bytes = Encoding.UTF8.GetBytes(newText);
+        return ShiftCharacterUp(Encoding.GetEncoding("ISO-8859-1").GetString(bytes));
+    }
+
+    string ShiftCharacterDown(string text)
+    {
+        string outText = "";
+        foreach (char letter in text)
+        {
+            outText += ((int)letter <= 256) ? letter :
+                (char)whiteSpaceCharacters[(int)(letter - 256)];
+        }
+        return outText;
+    }
+
+    string ShiftCharacterUp(string text)
+    {
+        string outText = "";
+        foreach (char letter in text)
+        {
+            outText += (char)encodedCharacters[(int)letter];
+        }
+        return outText;
+    }
+
+    void SetupWhiteSpaceShifts()
+    {
+        for (int i = 0, n = 0; i < 256; i++)
+        {
+            encodedCharacters[i] = i;
+            if (IsWhiteSpace(i))
+            {
+                encodedCharacters[i] = n + 256;
+                whiteSpaceCharacters[n++] = i;
+            }
+        }
+    }
+
+    bool IsWhiteSpace(int i)
+    {
+        //returns true if it is a whitespace character
+        return i <= 32 || (i >= 127 && i <= 160) || i == 173;
+    }
+
+    List<int> GetTokens(string text)
+    {
+        text = GetASCIIText(text);
+
+        // Start with a list of single characters
+        var inputTokens = new List<string>();
+        foreach(var letter in text)
+        {
+            inputTokens.Add(letter.ToString());
+        }
+
+        ApplyMerges(inputTokens);
+
+        //Find the ids of the words in the vocab
+        var ids = new List<int>();
+        foreach(var token in inputTokens)
+        {
+            if (vocab.TryGetValue(token, out int id))
+            {
+                ids.Add(id);
+            }
+        }
+
+        return ids;
+    }
+
+    void ApplyMerges(List<string> inputTokens)
+    {
+        foreach(var merge in merges)
+        {
+            string[] pair = merge.Split(' ');
+            int n = 0;
+            while (n >= 0)
+            {
+                n = inputTokens.IndexOf(pair[0], n);
+                if (n != -1 && n < inputTokens.Count - 1 && inputTokens[n + 1] == pair[1])
+                {
+                    inputTokens[n] += inputTokens[n + 1];
+                    inputTokens.RemoveAt(n + 1);
+                }
+                if (n != -1) n++;
+            }
+        }
+    }
+
+    private void OnDestroy()
+    {
+        engine?.Dispose();
+    }
+    
+}

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tinystories.sentis filter=lfs diff=lfs merge=lfs -text

info.json

@@ -0,0 +1,15 @@
+{
+    "code": [
+      "RunTinyStories.cs"
+    ],
+    "models": [
+        "tinystories.sentis"
+    ],
+    "data": [
+        "vocab.json",
+        "merges.txt"
+    ],
+    "version": [
+        "1.4.0"
+    ]
+}

tinystories (1).onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb65da6a70db2b11f977b136683616958339ea0a23b99552258421b6f2c1e4b
+size 436935967

tinystories.sentis

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7962eb7db56b241cc19cd3f0cffcf5d76d3c35639917f07effa6b3c242c91e9
+size 478818076