add 8-bit version

Author: Pierrci

gpt2/download.gradle

@@ -4,9 +4,10 @@ task downloadLiteModel {
     def downloadFiles = [
         "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-vocab.json": "gpt2-vocab.json",
         "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-merges.txt": "gpt2-merges.txt",
-        "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-fp16-64.tflite": "model.tflite",
-//        "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-64.tflite": "model.tflite",
-//        "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-64.tflite": "model.tflite",
+        "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-64-fp16.tflite": "model.tflite",     // FP16 quantization version
+//        "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-64-8bits.tflite": "model.tflite",  // 8-bit integers version
+//        "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-64.tflite": "model.tflite",        // "raw" version
+//        "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-64.tflite": "model.tflite",  // Distilled version
     ]
     downloadFiles.each { key, value ->
       download {