423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 06:12:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6046 from hiyouga/hiyouga/add_code_model

Browse Source 
[model] add qwen-coder and opencoder

Former-commit-id: 6c0847899d8b4f36bc362500f6ecb1c9cc14d7ea
This commit is contained in:
hoshi-hiyouga 2024-11-15 21:58:03 +08:00 committed by GitHub
commit e3a0640659
2 changed files with 68 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/llamafactory/data/template.py
View File

@ -911,6 +911,19 @@ _register_template(
)
_register_template(
name="opencoder",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
default_system="You are OpenCoder, created by OpenCoder Team.",
stop_words=["<|im_end|>"],
replace_eos=True,
replace_jinja_template=False,
)
_register_template(
name="orion",
format_user=StringFormatter(slots=["Human: {{content}}\n\nAssistant: ", {"eos_token"}]),

55
src/llamafactory/extras/constants.py
View File

@ -1105,6 +1105,29 @@ register_model_group(
)
register_model_group(
models={
"OpenCoder-1.5B-Base": {
DownloadSource.DEFAULT: "infly/OpenCoder-1.5B-Base",
DownloadSource.MODELSCOPE: "infly/OpenCoder-1.5B-Base",
},
"OpenCoder-8B-Base": {
DownloadSource.DEFAULT: "infly/OpenCoder-8B-Base",
DownloadSource.MODELSCOPE: "infly/OpenCoder-8B-Base",
},
"OpenCoder-1.5B-Instruct": {
DownloadSource.DEFAULT: "infly/OpenCoder-1.5B-Instruct",
DownloadSource.MODELSCOPE: "infly/OpenCoder-1.5B-Instruct",
},
"OpenCoder-8B-Instruct": {
DownloadSource.DEFAULT: "infly/OpenCoder-8B-Instruct",
DownloadSource.MODELSCOPE: "infly/OpenCoder-8B-Instruct",
},
},
template="opencoder",
)
register_model_group(
models={
"Orion-14B-Base": {
@ -1714,22 +1737,54 @@ register_model_group(
DownloadSource.DEFAULT: "Qwen/Qwen2.5-72B-Instruct-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-72B-Instruct-AWQ",
},
"Qwen2.5-Coder-0.5B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-0.5B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-0.5B",
},
"Qwen2.5-Coder-1.5B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-1.5B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-1.5B",
},
"Qwen2.5-Coder-3B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-3B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-3B",
},
"Qwen2.5-Coder-7B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-7B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-7B",
},
"Qwen2.5-Coder-14B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-14B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-14B",
},
"Qwen2.5-Coder-32B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-32B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-32B",
},
"Qwen2.5-Coder-0.5B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-0.5B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-0.5B-Instruct",
},
"Qwen2.5-Coder-1.5B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-1.5B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-1.5B-Instruct",
},
"Qwen2.5-Coder-3B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-3B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-3B-Instruct",
},
"Qwen2.5-Coder-7B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-7B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-7B-Instruct",
},
"Qwen2.5-Coder-14B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-14B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-14B-Instruct",
},
"Qwen2.5-Coder-32B-Instruct": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Coder-32B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Coder-32B-Instruct",
},
"Qwen2.5-Math-1.5B": {
DownloadSource.DEFAULT: "Qwen/Qwen2.5-Math-1.5B",
DownloadSource.MODELSCOPE: "qwen/Qwen2.5-Math-1.5B",