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

[misc] fix constants (#9008)

Browse Source
This commit is contained in:
Yaowei Zheng
2025-08-23 23:04:30 +08:00
committed by GitHub
parent 0ab0be9df2
commit ec41ef08aa
6 changed files with 40 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/data/formatter.py
View File

@@ -98,7 +98,7 @@ class FunctionFormatter(StringFormatter):
def apply(self, **kwargs) -> SLOTS:
content: str = kwargs.pop("content")
thought_words, thought = kwargs.pop("thought_words", None), None
if thought_words and len(thought_words)== 2:
if thought_words and len(thought_words) == 2:
regex = re.compile(rf"{re.escape(thought_words[0])}(.*?){re.escape(thought_words[1])}", re.DOTALL)
thought = re.search(regex, content)

8
src/llamafactory/data/template.py
View File

@@ -1855,19 +1855,17 @@ register_template(
)
#copied from seed_coder
# copied from seed_coder
register_template(
name="seed_oss",
format_user=StringFormatter(
slots=[{"bos_token"}, "user\n{{content}}", {"eos_token"}, {"bos_token"}, "assistant\n"]
),
format_system=StringFormatter(slots=[{"bos_token"}, "system\n{{content}}", {"eos_token"}]),
format_function=FunctionFormatter(
slots=[{"bos_token"}, "\n{{content}}", {"eos_token"}], tool_format="seed_oss"
),
format_function=FunctionFormatter(slots=[{"bos_token"}, "\n{{content}}", {"eos_token"}], tool_format="seed_oss"),
format_tools=ToolFormatter(tool_format="seed_oss"),
template_class=ReasoningTemplate,
thought_words=("<seed:think>", "</seed:think>")
thought_words=("<seed:think>", "</seed:think>"),
)

5
src/llamafactory/data/tool_utils.py
View File

@@ -355,6 +355,7 @@ class GLM4MOEToolUtils(QwenToolUtils):
return "\n".join(function_texts)
class SeedToolUtils(ToolUtils):
r"""Seed tool using template."""
@@ -387,8 +388,7 @@ class SeedToolUtils(ToolUtils):
def tool_extractor(content: str) -> Union[str, list["FunctionCall"]]:
results = []
regex = re.compile(
r"<seed:tool_call>\s*<function=\s*([^\s<]+)\s*(.*?)\s*</function>\s*</seed:tool_call>",
re.DOTALL
r"<seed:tool_call>\s*<function=\s*([^\s<]+)\s*(.*?)\s*</function>\s*</seed:tool_call>", re.DOTALL
)
for func_name, params_block in re.findall(regex, content):
args_dict = {}
@@ -405,6 +405,7 @@ class SeedToolUtils(ToolUtils):
return results
TOOLS = {
"default": DefaultToolUtils(),
"glm4": GLM4ToolUtils(),

27
src/llamafactory/extras/constants.py
View File

@@ -645,6 +645,7 @@ register_model_group(
template="falcon",
)
register_model_group(
models={
"Falcon-H1-0.5B-Base": {
@@ -1264,6 +1265,7 @@ register_model_group(
multimodal=True,
)
register_model_group(
models={
"Intern-S1-mini": {
@@ -1275,6 +1277,7 @@ register_model_group(
multimodal=True,
)
register_model_group(
models={
"Jamba-v0.1": {
@@ -3039,18 +3042,40 @@ register_model_group(
models={
"Seed-Coder-8B-Base": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-Coder-8B-Base",
DownloadSource.MODELSCOPE: "ByteDance-Seed/Seed-Coder-8B-Base",
},
"Seed-Coder-8B-Instruct": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-Coder-8B-Instruct",
DownloadSource.MODELSCOPE: "ByteDance-Seed/Seed-Coder-8B-Instruct",
},
"Seed-Coder-8B-Instruct-Reasoning": {
"Seed-Coder-8B-Thinking": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16",
DownloadSource.MODELSCOPE: "ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16",
},
},
template="seed_coder",
)
register_model_group(
models={
"Seed-OSS-36B-Base": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-OSS-36B-Base",
DownloadSource.MODELSCOPE: "ByteDance-Seed/Seed-OSS-36B-Base",
},
"Seed-OSS-36B-Base-woSyn": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-OSS-36B-Base-woSyn",
DownloadSource.MODELSCOPE: "ByteDance-Seed/Seed-OSS-36B-Base-woSyn",
},
"Seed-OSS-36B-Instruct": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-OSS-36B-Instruct",
DownloadSource.MODELSCOPE: "ByteDance-Seed/Seed-OSS-36B-Instruct",
},
},
template="seed_oss",
)
register_model_group(
models={
"Skywork-13B-Base": {