short-reply-0.6b Core ML package (prefill on ANE, decode GPU), tokenizer, host config

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,14 @@
+{
+  "package": "short_reply_0_6b.mlpackage",
+  "prefillLength": 160,
+  "cacheLength": 512,
+  "decodeLengths": [1, 64, 128, 256],
+  "layers": 28,
+  "kvHeads": 8,
+  "headDim": 128,
+  "padID": 151643,
+  "stopIDs": [151645, 151643],
+  "maxNewTokens": 32,
+  "systemPrompt": "Write one natural, very short reply to the social post as a separate person. React to a concrete detail in the post when possible. Do not invent facts or personal experiences. Use at most 12 words. Output only the reply.",
+  "maxPostCharacters": 2000
+}

short_reply_0_6b.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d848f2ce5066851927038202d9a929186adee2799fb29feadc652781c9a77b9
+size 1406867

short_reply_0_6b.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87eb1dee972ca6533effef3d3431f52f5e59777bf022ef7b39aa55daa907e78f
+size 757896128

short_reply_0_6b.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "E1ECD84E-BBE5-44DA-BAD0-26E92E5350D4": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "F6B2E484-283D-4DEE-91FD-47F56DE66872": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "F6B2E484-283D-4DEE-91FD-47F56DE66872"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650