423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 12:42:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix templates

Browse Source 
Former-commit-id: a73a979afd660afd3f2091c7b813a82b3a28645d
This commit is contained in:
hiyouga 2024-01-18 14:49:52 +08:00
parent 6af2f1f217
commit f7fcfeaa47
1 changed files with 30 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
src/llmtuner/data/template.py
View File

@ -286,6 +286,9 @@ register_template(
format_user=StringFormatter(container=[ format_user=StringFormatter(container=[
"Human: {{content}}###Assistant:" "Human: {{content}}###Assistant:"
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
system=( system=(
"A chat between a curious human and an artificial intelligence assistant. " "A chat between a curious human and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the human's questions." "The assistant gives helpful, detailed, and polite answers to the human's questions."
@ -307,6 +310,9 @@ register_template(
"{{content}}", "{{content}}",
{"token": "<reserved_103>"} {"token": "<reserved_103>"}
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
efficient_eos=True efficient_eos=True
) )
@ -318,6 +324,9 @@ register_template(
"{{content}}", "{{content}}",
{"token": "<reserved_107>"} {"token": "<reserved_107>"}
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
efficient_eos=True efficient_eos=True
) )
@ -348,6 +357,9 @@ register_template(
format_user=StringFormatter(container=[ format_user=StringFormatter(container=[
"[Round {{idx}}]\n\n问：{{content}}\n\n答：" "[Round {{idx}}]\n\n问：{{content}}\n\n答："
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
format_system=StringFormatter(container=[ format_system=StringFormatter(container=[
{"token": "[gMASK]"}, {"token": "[gMASK]"},
{"token": "sop"}, {"token": "sop"},
@ -422,6 +434,9 @@ register_template(
format_user=StringFormatter(container=[ format_user=StringFormatter(container=[
"### Instruction:\n{{content}}\n### Response:\n" "### Instruction:\n{{content}}\n### Response:\n"
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
system=( system=(
"You are an AI programming assistant, utilizing the Deepseek Coder model, " "You are an AI programming assistant, utilizing the Deepseek Coder model, "
"developed by Deepseek Company, and you only answer questions related to computer science. " "developed by Deepseek Company, and you only answer questions related to computer science. "
@ -460,6 +475,9 @@ register_template(
format_user=StringFormatter(container=[ format_user=StringFormatter(container=[
"User: {{content}}\nFalcon:" "User: {{content}}\nFalcon:"
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
separator=[ separator=[
"\n" "\n"
], ],
@ -474,6 +492,9 @@ register_template(
{"token": "<eoh>"}, {"token": "<eoh>"},
"\n<|Bot|>:" "\n<|Bot|>:"
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
separator=[ separator=[
{"token": "<eoa>"}, {"token": "<eoa>"},
"\n" "\n"
@ -495,6 +516,9 @@ register_template(
{"token": "[UNUSED_TOKEN_146]"}, {"token": "[UNUSED_TOKEN_146]"},
"assistant\n" "assistant\n"
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
format_system=StringFormatter(container=[ format_system=StringFormatter(container=[
{"token": "[UNUSED_TOKEN_146]"}, {"token": "[UNUSED_TOKEN_146]"},
"system\n{{content}}", "system\n{{content}}",
@ -557,6 +581,9 @@ register_template(
{"token": "<|end_of_turn|>"}, {"token": "<|end_of_turn|>"},
"GPT4 Correct Assistant:" "GPT4 Correct Assistant:"
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
separator=[ separator=[
{"token": "<|end_of_turn|>"} {"token": "<|end_of_turn|>"}
], ],
@ -603,6 +630,9 @@ register_template(
"\n", "\n",
{"token": "<|assistant|>"} {"token": "<|assistant|>"}
]), ]),
format_assistant=StringFormatter(container=[
"{{content}}"
]),
format_system=StringFormatter(container=[ format_system=StringFormatter(container=[
{"token": "<|system|>"}, {"token": "<|system|>"},
"\n{{content}}", "\n{{content}}",