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
This commit is contained in:
HanishKVC 2024-04-25 18:00:01 +05:30
parent bf1167bfdb
commit b9e31304a5

View file

@ -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
},