From b9e31304a529d63e8ffad3422044d47a8d5f4744 Mon Sep 17 00:00:00 2001
From: HanishKVC <hanishkvc@gmail.com>
Date: Thu, 25 Apr 2024 18:00:01 +0530
Subject: [PATCH] ChatON: Update to new detailed format wrt llama2 and llama3

Wrt llama2
* add bos wrt llama2 system and user begins, but not assistant
* split system suffix into suffix and end, and add systemuser-system
  flags so that end can be avoided wrt system+user message combo
* add eos wrt assistant end
* With these potentially this should work with main and server flows

Wrt llama3
* add empty begin, end fields and systemuser-system flags
* This should potentially work with main and server flows
---
 examples/chaton_meta.json | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/examples/chaton_meta.json b/examples/chaton_meta.json
index 25f05a170..333ad620e 100644
--- a/examples/chaton_meta.json
+++ b/examples/chaton_meta.json
@@ -6,19 +6,26 @@
 			"end": ""
 		},
 		"system": {
+			"begin": "<s>",
 			"prefix": "[INST] <<SYS>>\n",
-			"suffix": "\n<</SYS>> [/INST]\n\n"
+			"suffix": "\n<</SYS>> ",
+			"end": "[/INST]\n\n"
 		},
 		"user": {
-			"begin": "",
+			"begin": "<s>",
 			"prefix": "[INST] ",
-			"suffix": " [/INST]\n\n"
+			"suffix": " [/INST]\n\n",
+			"end": ""
 		},
 		"assistant": {
+			"begin": "",
 			"prefix": "",
-			"suffix": "</s>"
+			"suffix": "",
+			"end": "</s>"
 		},
 		"reverse-prompt": "</s>",
+		"systemuser-system-has-suffix": true,
+		"systemuser-system-has-end": false,
 		"systemuser-1st-user-has-begin": false,
 		"systemuser-1st-user-has-prefix": false
 	},
@@ -28,19 +35,26 @@
 			"end": ""
 		},
 		"system": {
+			"begin": "",
 			"prefix": "<|start_header_id|>system<|end_header_id|>\n",
-			"suffix": "<|eot_id|>\n\n"
+			"suffix": "<|eot_id|>\n\n",
+			"end": ""
 		},
 		"user": {
 			"begin": "",
 			"prefix": "<|start_header_id|>user<|end_header_id|>\n",
-			"suffix": "<|eot_id|>\n\n"
+			"suffix": "<|eot_id|>\n\n",
+			"end": ""
 		},
 		"assistant": {
+			"begin": "",
 			"prefix": "<|start_header_id|>assistant<|end_header_id|>\n",
-			"suffix": "<|eot_id|>\n\n"
+			"suffix": "<|eot_id|>\n\n",
+			"end": ""
 		},
 		"reverse-prompt": "<|eot_id|>",
+		"systemuser-system-has-suffix": true,
+		"systemuser-system-has-end": true,
 		"systemuser-1st-user-has-begin": true,
 		"systemuser-1st-user-has-prefix": true
 	},