[misc] fix constants (#9008)

README.md

@@ -5,7 +5,7 @@
 [![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors)
 [![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml)
 [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
-[![Citation](https://img.shields.io/badge/citation-760-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
+[![Citation](https://img.shields.io/badge/citation-818-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
 [![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags)
 
 [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
@@ -124,12 +124,12 @@ Choose your path:
 
 [25/08/06] We supported fine-tuning the **[GPT-OSS](https://github.com/openai/gpt-oss)** models. See [PR #8826](https://github.com/hiyouga/LLaMA-Factory/pull/8826) to get started.
 
+<details><summary>Full Changelog</summary>
+
 [25/07/02] We supported fine-tuning the **[GLM-4.1V-9B-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)** model.
 
 [25/04/28] We supported fine-tuning the **[Qwen3](https://qwenlm.github.io/blog/qwen3/)** model family.
 
-<details><summary>Full Changelog</summary>
-
 [25/04/21] We supported the **[Muon](https://github.com/KellerJordan/Muon)** optimizer. See [examples](examples/README.md) for usage. Thank [@tianshijing](https://github.com/tianshijing)'s PR.
 
 [25/04/16] We supported fine-tuning the **[InternVL3](https://huggingface.co/OpenGVLab/InternVL3-8B)** model. See [PR #7258](https://github.com/hiyouga/LLaMA-Factory/pull/7258) to get started.

README_zh.md

@@ -5,7 +5,7 @@
 [![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors)
 [![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml)
 [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/)
-[![Citation](https://img.shields.io/badge/citation-760-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
+[![Citation](https://img.shields.io/badge/citation-818-green)](https://scholar.google.com/scholar?cites=12620864006390196564)
 [![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags)
 
 [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai)
@@ -126,12 +126,12 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 
 [25/08/06] 我们支持了 **[GPT-OSS](https://github.com/openai/gpt-oss)** 模型的微调。查看 [PR #8826](https://github.com/hiyouga/LLaMA-Factory/pull/8826) 以使用。
 
+<details><summary>展开日志</summary>
+
 [25/07/02] 我们支持了 **[GLM-4.1V-9B-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)** 模型的微调。
 
 [25/04/28] 我们支持了 **[Qwen3](https://qwenlm.github.io/blog/qwen3/)** 系列模型的微调。
 
-<details><summary>展开日志</summary>
-
 [25/04/21] 我们支持了 **[Muon](https://github.com/KellerJordan/Muon)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@tianshijing](https://github.com/tianshijing) 的 PR。
 
 [25/04/16] 我们支持了 **[InternVL3](https://huggingface.co/OpenGVLab/InternVL3-8B)** 模型的微调。查看 [PR #7258](https://github.com/hiyouga/LLaMA-Factory/pull/7258) 以使用。

src/llamafactory/data/template.py

@@ -1862,12 +1862,10 @@ register_template(
         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(
+    format_function=FunctionFormatter(slots=[{"bos_token"}, "\n{{content}}", {"eos_token"}], tool_format="seed_oss"),
-        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>"),
 )
 
 

src/llamafactory/data/tool_utils.py

@@ -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>",
+            r"<seed:tool_call>\s*<function=\s*([^\s<]+)\s*(.*?)\s*</function>\s*</seed:tool_call>", re.DOTALL
-            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(),

src/llamafactory/extras/constants.py

@@ -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": {