.gitattributes

@@ -1,35 +0,0 @@
-*.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

config.pbtxt

@@ -0,0 +1,71 @@
+# Triton backend to use
+name: "Llama-3.2-1B-Instruct"
+backend: "tensorflow"
+platform: "tensorflow_savedmodel"
+max_batch_size: 0
+
+input [
+  {
+    name: "text_input"
+    data_type: TYPE_STRING
+    dims: [ apple ]
+  },
+  {
+    name: "max_length"
+    data_type: TYPE_INT32
+    dims: [ 1 ]
+  },
+  {
+    name: "max_new_tokens"
+    data_type: TYPE_INT32
+    dims: [ 1 ]
+  },
+  {
+    name: "do_sample"
+    data_type: TYPE_BOOL
+    dims: [ 1 ]
+  },
+  {
+    name: "top_k"
+    data_type: TYPE_INT32
+    dims: [ 1 ]
+  },
+  {
+    name: "top_p"
+    data_type: TYPE_FP32
+    dims: [ 1 ]
+  },
+  {
+    name: "temperature"
+    data_type: TYPE_FP32
+    dims: [ 1 ]
+  },
+  {
+    name: "repetition_penalty"
+    data_type: TYPE_FP32
+    dims: [ 1 ]
+  },
+  {
+    name: "stream"
+    data_type: TYPE_BOOL
+    dims: [ 1 ]
+  }
+]
+
+output [
+  {
+    name: "text_output"
+    data_type: TYPE_STRING
+    dims: [ -1 ]
+  }
+]
+
+
+
+
+instance_group [
+  {
+    kind: KIND_AUTO
+    count: 1
+  }
+]