p04798526
/
LLaMA-Factory-Mirror
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add models

This commit is contained in:
hiyouga 2024-02-06 14:57:23 +08:00
parent ccabb5b04a
commit 85622ae757
2 changed files with 16 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/data/template.py
View File

@ -376,7 +376,8 @@ register_template(
register_template( register_template(
name="deepseekcoder", name="deepseekcoder",
format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n### Response:\n"]), format_user=StringFormatter(slots=["### Instruction:\n{{content}}\n### Response:"]),
format_assistant=StringFormatter(slots=["\n", "{{content}}"]),
format_separator=EmptyFormatter(slots=["\n", {"token": "<|EOT|>"}, "\n"]), format_separator=EmptyFormatter(slots=["\n", {"token": "<|EOT|>"}, "\n"]),
default_system=( default_system=(
"You are an AI programming assistant, utilizing the Deepseek Coder model, " "You are an AI programming assistant, utilizing the Deepseek Coder model, "

33
src/llmtuner/extras/constants.py
View File

@ -219,22 +219,32 @@ register_model_group(
register_model_group( register_model_group(
models={ models={
"DeepSeekLLM-7B-Base": { "DeepSeek-LLM-7B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-base", DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-base",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-base", DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-base",
}, },
"DeepSeekLLM-67B-Base": { "DeepSeek-LLM-67B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-base", DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-base",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-base", DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-base",
}, },
"DeepSeekLLM-7B-Chat": { "DeepSeek-LLM-7B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-chat", DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-7b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-chat", DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-7b-chat",
}, },
"DeepSeekLLM-67B-Chat": { "DeepSeek-LLM-67B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-chat", DownloadSource.DEFAULT: "deepseek-ai/deepseek-llm-67b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-chat", DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-llm-67b-chat",
}, },
"DeepSeek-Math-7B-Base": {DownloadSource.DEFAULT: "deepseek-ai/deepseek-math-7b-base"},
"DeepSeek-Math-7B-Chat": {DownloadSource.DEFAULT: "deepseek-ai/deepseek-math-7b-instruct"},
"DeepSeek-MoE-16B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base",
},
"DeepSeek-MoE-16B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
},
}, },
template="deepseek", template="deepseek",
) )
@ -265,21 +275,6 @@ register_model_group(
) )
register_model_group(
models={
"DeepSeekMoE-16B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base",
},
"DeepSeekMoE-16B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
},
},
template="deepseek",
)
register_model_group( register_model_group(
models={ models={
"Falcon-7B": { "Falcon-7B": {