add models

Former-commit-id: b9eaadde8b5f4b9f89fa7bb910b325fcf9c84434
This commit is contained in:
hiyouga
2023-11-30 19:16:13 +08:00
parent 08d5340bd8
commit 7ef8f46591
4 changed files with 53 additions and 10 deletions

View File

@@ -408,18 +408,31 @@ register_template(
"{{system}}"
],
prompt=[
"### Instruction:\n{{query}}\n\n### Response:\n"
"User: {{query}}\n\nAssistant:"
],
system="",
sep=[]
)
register_template(
name="deepseekcoder",
prefix=[
"{{system}}"
],
prompt=[
"### Instruction:\n{{query}}\n### Response:\n"
],
system=(
"You are an AI programming assistant, utilizing the Deepseek Coder model, "
"developed by Deepseek Company, and you only answer questions related to computer science. "
"For politically sensitive questions, security and privacy issues, "
"and other non-computer science questions, you will refuse to answer."
"and other non-computer science questions, you will refuse to answer\n"
),
sep=[
"\n",
{"token": "<|EOT|>"},
"\n\n"
"\n"
],
stop_words=[
"<|EOT|>"

View File

@@ -131,6 +131,28 @@ register_model_group(
)
register_model_group(
models={
"DeepseekLLM-7B-Base": "deepseek-ai/deepseek-llm-7b-base",
"DeepseekLLM-67B-Base": "deepseek-ai/deepseek-llm-67b-base",
"DeepseekLLM-7B-Chat": "deepseek-ai/deepseek-llm-7b-chat",
"DeepseekLLM-67B-Chat": "deepseek-ai/deepseek-llm-67b-chat"
},
template="deepseek"
)
register_model_group(
models={
"DeepseekCoder-6.7B-Base": "deepseek-ai/deepseek-coder-6.7b-base",
"DeepseekCoder-6.7B-Chat": "deepseek-ai/deepseek-coder-6.7b-instruct",
"DeepseekCoder-33B-Base": "deepseek-ai/deepseek-coder-33b-base",
"DeepseekCoder-33B-Chat": "deepseek-ai/deepseek-coder-33b-instruct"
},
template="deepseekcoder"
)
register_model_group(
models={
"Falcon-7B": "tiiuae/falcon-7b",
@@ -214,14 +236,22 @@ register_model_group(
register_model_group(
models={
"Qwen-1.8B": "Qwen/Qwen-1_8B",
"Qwen-7B": "Qwen/Qwen-7B",
"Qwen-14B": "Qwen/Qwen-14B",
"Qwen-72B": "Qwen/Qwen-72B",
"Qwen-1.8B-Chat": "Qwen/Qwen-1_8B-Chat",
"Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
"Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
"Qwen-72B-Chat": "Qwen/Qwen-72B-Chat",
"Qwen-1.8B-int8-Chat": "Qwen/Qwen-1_8B-Chat-Int8",
"Qwen-1.8B-int4-Chat": "Qwen/Qwen-1_8B-Chat-Int4",
"Qwen-7B-int8-Chat": "Qwen/Qwen-7B-Chat-Int8",
"Qwen-7B-int4-Chat": "Qwen/Qwen-7B-Chat-Int4",
"Qwen-14B-int8-Chat": "Qwen/Qwen-14B-Chat-Int8",
"Qwen-14B-int4-Chat": "Qwen/Qwen-14B-Chat-Int4"
"Qwen-14B-int4-Chat": "Qwen/Qwen-14B-Chat-Int4",
"Qwen-72B-int8-Chat": "Qwen/Qwen-72B-Chat-Int8",
"Qwen-72B-int4-Chat": "Qwen/Qwen-72B-Chat-Int4"
},
module="c_attn",
template="qwen"