423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 11:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] add mimo7b (#7946)

Browse Source
This commit is contained in:
Kingsley
2025-05-06 23:10:30 +08:00
committed by GitHub
parent c7250c371f
commit d564fc584b
4 changed files with 43 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/llamafactory/data/template.py
View File

@@ -1324,6 +1324,24 @@ register_template(
)
# copied from qwen template
register_template(
name="mimo",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_assistant=StringFormatter(slots=["{{content}}<|im_end|>\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_function=FunctionFormatter(slots=["{{content}}<|im_end|>\n"], tool_format="qwen"),
format_observation=StringFormatter(
slots=["<|im_start|>user\n<tool_response>\n{{content}}\n</tool_response><|im_end|>\n<|im_start|>assistant\n"]
),
format_tools=ToolFormatter(tool_format="qwen"),
default_system="You are a helpful assistant.",
stop_words=["<|im_end|>"],
replace_eos=True,
template_class=ReasoningTemplate,
)
# copied from chatml template
register_template(
name="minicpm_v",

23
src/llamafactory/extras/constants.py
View File

@@ -1416,6 +1416,29 @@ register_model_group(
)
register_model_group(
models={
"MiMo-7B-Base": {
DownloadSource.DEFAULT: "XiaomiMiMo/MiMo-7B-Base",
DownloadSource.MODELSCOPE: "XiaomiMiMo/MiMo-7B-Base",
},
"MiMo-7B-Instruct": {
DownloadSource.DEFAULT: "XiaomiMiMo/MiMo-7B-SFT",
DownloadSource.MODELSCOPE: "XiaomiMiMo/MiMo-7B-SFT",
},
"MiMo-7B-Instruct-RL": {
DownloadSource.DEFAULT: "XiaomiMiMo/MiMo-7B-RL",
DownloadSource.MODELSCOPE: "XiaomiMiMo/MiMo-7B-RL",
},
"MiMo-7B-RL-ZERO": {
DownloadSource.DEFAULT: "XiaomiMiMo/MiMo-7B-RL-ZERO",
DownloadSource.MODELSCOPE: "XiaomiMiMo/MiMo-7B-RL-ZERO",
},
},
template="mimo",
)
register_model_group(
models={
"MiniCPM-2B-SFT-Chat": {