From 26e897e861464de58fd0ffd01e56992a5b7da130 Mon Sep 17 00:00:00 2001
From: huniu20 <huniumail@gmail.com>
Date: Wed, 9 Oct 2024 17:21:37 +0800
Subject: [PATCH 1/8] 1. add modelers hub support

Former-commit-id: 24ebe187e360753666b768685a0dcc78054bb702
---
 README.md                        | 20 ++++++++++++++++++--
 README_zh.md                     | 20 ++++++++++++++++++--
 src/llamafactory/__init__.py     |  1 +
 src/llamafactory/data/loader.py  | 21 +++++++++++++++++++--
 src/llamafactory/data/parser.py  | 18 +++++++++++++-----
 src/llamafactory/extras/misc.py  | 29 +++++++++++++++++++++--------
 src/llamafactory/model/loader.py |  4 ++--
 7 files changed, 92 insertions(+), 21 deletions(-)

diff --git a/README.md b/README.md
index 3359c10d..40253b16 100644
--- a/README.md
+++ b/README.md
@@ -75,6 +75,8 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 ## Changelog
 
+[24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)** for Chinese mainland users. See [this tutorial](#download-from-modelers-hub) for usage.
+
 [24/09/19] We support fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models.
 
 [24/08/30] We support fine-tuning the **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** models. Thank [@simonJJJ](https://github.com/simonJJJ)'s PR.
@@ -363,7 +365,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
 
-Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, quality
+Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, quality, openmind
 
 > [!TIP]
 > Use `pip install --no-deps -e .` to resolve package conflicts.
@@ -415,7 +417,7 @@ Download the pre-built Docker images: [32GB](http://mirrors.cn-central-221.ovaij
 
 ### Data Preparation
 
-Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope hub or load the dataset in local disk.
+Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can use datasets on HuggingFace hub, ModelScope hub, modelers hub or load the dataset in local disk.
 
 > [!NOTE]
 > Please update `data/dataset_info.json` to use your custom dataset.
@@ -483,6 +485,7 @@ docker build -f ./docker/docker-cuda/Dockerfile \
 docker run -dit --gpus=all \
     -v ./hf_cache:/root/.cache/huggingface \
     -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
     -v ./data:/app/data \
     -v ./output:/app/output \
     -p 7860:7860 \
@@ -507,6 +510,7 @@ docker build -f ./docker/docker-npu/Dockerfile \
 docker run -dit \
     -v ./hf_cache:/root/.cache/huggingface \
     -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
     -v ./data:/app/data \
     -v ./output:/app/output \
     -v /usr/local/dcmi:/usr/local/dcmi \
@@ -540,6 +544,7 @@ docker build -f ./docker/docker-rocm/Dockerfile \
 docker run -dit \
     -v ./hf_cache:/root/.cache/huggingface \
     -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
     -v ./data:/app/data \
     -v ./output:/app/output \
     -v ./saves:/app/saves \
@@ -560,6 +565,7 @@ docker exec -it llamafactory bash
 
 - `hf_cache`: Utilize Hugging Face cache on the host machine. Reassignable if a cache already exists in a different directory.
 - `ms_cache`: Similar to Hugging Face cache but for ModelScope users.
+- `om_cache`: Similar to Hugging Face cache but for Modelers users.
 - `data`: Place datasets on this dir of the host machine so that they can be selected on LLaMA Board GUI.
 - `output`: Set export dir to this location so that the merged result can be accessed directly on the host machine.
 
@@ -584,6 +590,16 @@ export USE_MODELSCOPE_HUB=1 # `set USE_MODELSCOPE_HUB=1` for Windows
 
 Train the model by specifying a model ID of the ModelScope Hub as the `model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `LLM-Research/Meta-Llama-3-8B-Instruct`.
 
+### Download from Modelers Hub
+
+You can also use Modelers Hub to download models and datasets.
+
+```bash
+export USE_OPENMIND_HUB=1 # `set USE_OPENMIND_HUB=1` for Windows
+```
+
+Train the model by specifying a model ID of the Modelers Hub as the `model_name_or_path`. You can find a full list of model IDs at [Modelers Hub](https://modelers.cn/models), e.g., `TeleAI/TeleChat-7B-pt`.
+
 ### Use W&B Logger
 
 To use [Weights & Biases](https://wandb.ai) for logging experimental results, you need to add the following arguments to yaml files.
diff --git a/README_zh.md b/README_zh.md
index 20e86853..61aa860c 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -75,6 +75,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 </details>
 
 ## 更新日志
+[24/10/09] 我们支持了从 **[魔乐社区](https://modelers.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔乐社区下载)。
 
 [24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。
 
@@ -364,7 +365,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
 
-可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality
+可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality、openmind
 
 > [!TIP]
 > 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
@@ -416,7 +417,7 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 
 ### 数据准备
 
-关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace / ModelScope 上的数据集或加载本地数据集。
+关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace , ModelScope 或者 Modelers 上的数据集或加载本地数据集。
 
 > [!NOTE]
 > 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
@@ -484,6 +485,7 @@ docker build -f ./docker/docker-cuda/Dockerfile \
 docker run -dit --gpus=all \
     -v ./hf_cache:/root/.cache/huggingface \
     -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
     -v ./data:/app/data \
     -v ./output:/app/output \
     -p 7860:7860 \
@@ -508,6 +510,7 @@ docker build -f ./docker/docker-npu/Dockerfile \
 docker run -dit \
     -v ./hf_cache:/root/.cache/huggingface \
     -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
     -v ./data:/app/data \
     -v ./output:/app/output \
     -v /usr/local/dcmi:/usr/local/dcmi \
@@ -541,6 +544,7 @@ docker build -f ./docker/docker-rocm/Dockerfile \
 docker run -dit \
     -v ./hf_cache:/root/.cache/huggingface \
     -v ./ms_cache:/root/.cache/modelscope \
+    -v ./om_cache:/root/.cache/openmind \
     -v ./data:/app/data \
     -v ./output:/app/output \
     -v ./saves:/app/saves \
@@ -561,6 +565,7 @@ docker exec -it llamafactory bash
 
 - `hf_cache`：使用宿主机的 Hugging Face 缓存文件夹，允许更改为新的目录。
 - `ms_cache`：类似 Hugging Face 缓存文件夹，为 ModelScope 用户提供。
+- `om_cache`：类似 Hugging Face 缓存文件夹，为 Modelers 用户提供。
 - `data`：宿主机中存放数据集的文件夹路径。
 - `output`：将导出目录设置为该路径后，即可在宿主机中访问导出后的模型。
 
@@ -585,6 +590,17 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 
 将 `model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔搭社区](https://modelscope.cn/models)查看所有可用的模型，例如 `LLM-Research/Meta-Llama-3-8B-Instruct`。
 
+### 从魔乐社区下载
+
+您也可以通过下述方法使用魔乐社区，在魔乐社区上下载数据集和模型。
+
+```bash
+export USE_OPENMIND_HUB=1 # Windows 使用 `set USE_OPENMIND_HUB=1`
+```
+
+将 `model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔乐社区](https://modelers.cn/models)查看所有可用的模型，例如 `TeleAI/TeleChat-7B-pt`。
+
+
 ### 使用 W&B 面板
 
 若要使用 [Weights & Biases](https://wandb.ai) 记录实验数据，请在 yaml 文件中添加下面的参数。
diff --git a/src/llamafactory/__init__.py b/src/llamafactory/__init__.py
index ffc8c9ad..dd5d1a01 100644
--- a/src/llamafactory/__init__.py
+++ b/src/llamafactory/__init__.py
@@ -38,6 +38,7 @@ Force check imports: FORCE_CHECK_IMPORTS=1
 Force using torchrun: FORCE_TORCHRUN=1
 Set logging verbosity: LLAMAFACTORY_VERBOSITY=WARN
 Use modelscope: USE_MODELSCOPE_HUB=1
+Use openmind: USE_OPENMIND_HUB=1
 """
 
 from .extras.env import VERSION
diff --git a/src/llamafactory/data/loader.py b/src/llamafactory/data/loader.py
index 362d57e9..03a38fa8 100644
--- a/src/llamafactory/data/loader.py
+++ b/src/llamafactory/data/loader.py
@@ -53,7 +53,7 @@ def _load_single_dataset(
     """
     logger.info("Loading dataset {}...".format(dataset_attr))
     data_path, data_name, data_dir, data_files = None, None, None, None
-    if dataset_attr.load_from in ["hf_hub", "ms_hub"]:
+    if dataset_attr.load_from in ["om_hub", "hf_hub", "ms_hub"]:
         data_path = dataset_attr.dataset_name
         data_name = dataset_attr.subset
         data_dir = dataset_attr.folder
@@ -84,7 +84,24 @@ def _load_single_dataset(
     else:
         raise NotImplementedError("Unknown load type: {}.".format(dataset_attr.load_from))
 
-    if dataset_attr.load_from == "ms_hub":
+    if dataset_attr.load_from == "om_hub":
+        try:
+            from openmind import OmDataset
+            from openmind.utils.hub import OM_DATASETS_CACHE
+            cache_dir = model_args.cache_dir or OM_DATASETS_CACHE
+            dataset = OmDataset.load_dataset(
+                path=data_path,
+                name=data_name,
+                data_dir=data_dir,
+                data_files=data_files,
+                split=data_args.split,
+                cache_dir=cache_dir,
+                token=model_args.ms_hub_token,
+                streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
+            )
+        except ImportError:
+            raise ImportError("Please install openmind via `pip install openmind -U`")
+    elif dataset_attr.load_from == "ms_hub":
         require_version("modelscope>=1.11.0", "To fix: pip install modelscope>=1.11.0")
         from modelscope import MsDataset
         from modelscope.utils.config_ds import MS_DATASETS_CACHE
diff --git a/src/llamafactory/data/parser.py b/src/llamafactory/data/parser.py
index 15a6eab8..696cd488 100644
--- a/src/llamafactory/data/parser.py
+++ b/src/llamafactory/data/parser.py
@@ -20,7 +20,7 @@ from typing import Any, Dict, List, Literal, Optional, Sequence
 from transformers.utils import cached_file
 
 from ..extras.constants import DATA_CONFIG
-from ..extras.misc import use_modelscope
+from ..extras.misc import use_openmind, use_modelscope
 
 
 @dataclass
@@ -97,8 +97,13 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
 
     dataset_list: List["DatasetAttr"] = []
     for name in dataset_names:
-        if dataset_info is None:  # dataset_dir is ONLINE
-            load_from = "ms_hub" if use_modelscope() else "hf_hub"
+        if dataset_info is None: # dataset_dir is ONLINE
+            if use_openmind():
+                load_from = "om_hub"
+            if use_modelscope():
+                load_from = "ms_hub"
+            if load_from is None:
+                load_from = "hf_hub"
             dataset_attr = DatasetAttr(load_from, dataset_name=name)
             dataset_list.append(dataset_attr)
             continue
@@ -106,11 +111,14 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
         if name not in dataset_info:
             raise ValueError("Undefined dataset {} in {}.".format(name, DATA_CONFIG))
 
+        has_om_url = "om_hub_url" in dataset_info[name]
         has_hf_url = "hf_hub_url" in dataset_info[name]
         has_ms_url = "ms_hub_url" in dataset_info[name]
 
-        if has_hf_url or has_ms_url:
-            if (use_modelscope() and has_ms_url) or (not has_hf_url):
+        if has_om_url or has_hf_url or has_ms_url:
+            if (use_openmind() and has_om_url) or (not has_hf_url):
+                dataset_attr = DatasetAttr("om_hub", dataset_name=dataset_info[name]["om_hub_url"])
+            elif (use_modelscope() and has_ms_url) or (not has_hf_url):
                 dataset_attr = DatasetAttr("ms_hub", dataset_name=dataset_info[name]["ms_hub_url"])
             else:
                 dataset_attr = DatasetAttr("hf_hub", dataset_name=dataset_info[name]["hf_hub_url"])
diff --git a/src/llamafactory/extras/misc.py b/src/llamafactory/extras/misc.py
index 7d0a457a..4c42900d 100644
--- a/src/llamafactory/extras/misc.py
+++ b/src/llamafactory/extras/misc.py
@@ -231,18 +231,31 @@ def torch_gc() -> None:
         torch.cuda.empty_cache()
 
 
-def try_download_model_from_ms(model_args: "ModelArguments") -> str:
-    if not use_modelscope() or os.path.exists(model_args.model_name_or_path):
+def try_download_model_from_other_hub(model_args: "ModelArguments") -> str:
+    if (not use_openmind() and not use_modelscope()) or os.path.exists(model_args.model_name_or_path):
         return model_args.model_name_or_path
 
-    try:
-        from modelscope import snapshot_download
+    if use_openmind():
+        try:
+            import openmind
+            from openmind.utils.hub import snapshot_download
 
-        revision = "master" if model_args.model_revision == "main" else model_args.model_revision
-        return snapshot_download(model_args.model_name_or_path, revision=revision, cache_dir=model_args.cache_dir)
-    except ImportError:
-        raise ImportError("Please install modelscope via `pip install modelscope -U`")
+            revision = "main" if model_args.model_revision == "main" else model_args.model_revision
+            return snapshot_download(model_args.model_name_or_path, revision=revision, cache_dir=model_args.cache_dir)
+        except ImportError:
+            raise ImportError("Please install openmind and openmind_hub via `pip install openmind -U`")
 
+    if use_modelscope():
+        try:
+            from modelscope import snapshot_download
+
+            revision = "master" if model_args.model_revision == "main" else model_args.model_revision
+            return snapshot_download(model_args.model_name_or_path, revision=revision, cache_dir=model_args.cache_dir)
+        except ImportError:
+            raise ImportError("Please install modelscope via `pip install modelscope -U`")
+
+def use_openmind() -> bool:
+    return os.environ.get("USE_OPENMIND_HUB", "0").lower() in ["true", "1"]
 
 def use_modelscope() -> bool:
     return os.environ.get("USE_MODELSCOPE_HUB", "0").lower() in ["true", "1"]
diff --git a/src/llamafactory/model/loader.py b/src/llamafactory/model/loader.py
index fb71498b..7613c092 100644
--- a/src/llamafactory/model/loader.py
+++ b/src/llamafactory/model/loader.py
@@ -19,7 +19,7 @@ from transformers import AutoConfig, AutoModelForCausalLM, AutoModelForVision2Se
 from trl import AutoModelForCausalLMWithValueHead
 
 from ..extras.logging import get_logger
-from ..extras.misc import count_parameters, skip_check_imports, try_download_model_from_ms
+from ..extras.misc import count_parameters, skip_check_imports, try_download_model_from_other_hub
 from .adapter import init_adapter
 from .model_utils.liger_kernel import apply_liger_kernel
 from .model_utils.misc import register_autoclass
@@ -50,7 +50,7 @@ def _get_init_kwargs(model_args: "ModelArguments") -> Dict[str, Any]:
     Note: including inplace operation of model_args.
     """
     skip_check_imports()
-    model_args.model_name_or_path = try_download_model_from_ms(model_args)
+    model_args.model_name_or_path = try_download_model_from_other_hub(model_args)
     return {
         "trust_remote_code": True,
         "cache_dir": model_args.cache_dir,

From 132c1f1b0fbd39120e8175540e2654a441a68b14 Mon Sep 17 00:00:00 2001
From: huniu20 <huniumail@gmail.com>
Date: Thu, 10 Oct 2024 16:46:34 +0800
Subject: [PATCH 2/8] 1. add model and dataset info to support webui

Former-commit-id: 0f669f221a31622ec7a53d0baab5da6a7891f9b6
---
 README.md                            |  2 +-
 README_zh.md                         |  3 +--
 data/dataset_info.json               |  6 ++++--
 src/llamafactory/data/loader.py      |  2 +-
 src/llamafactory/data/parser.py      |  1 +
 src/llamafactory/extras/constants.py | 12 ++++++++++++
 src/llamafactory/webui/common.py     |  9 ++++++++-
 7 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 40253b16..621a1c21 100644
--- a/README.md
+++ b/README.md
@@ -417,7 +417,7 @@ Download the pre-built Docker images: [32GB](http://mirrors.cn-central-221.ovaij
 
 ### Data Preparation
 
-Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can use datasets on HuggingFace hub, ModelScope hub, modelers hub or load the dataset in local disk.
+Please refer to [data/README.md](data/README.md) for checking the details about the format of dataset files. You can either use datasets on HuggingFace / ModelScope / Modelers hub or load the dataset in local disk.
 
 > [!NOTE]
 > Please update `data/dataset_info.json` to use your custom dataset.
diff --git a/README_zh.md b/README_zh.md
index 61aa860c..1d18ad16 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -417,8 +417,7 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 
 ### 数据准备
 
-关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace , ModelScope 或者 Modelers 上的数据集或加载本地数据集。
-
+关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace / ModelScope / Modelers 上的数据集或加载本地数据集。
 > [!NOTE]
 > 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
 
diff --git a/data/dataset_info.json b/data/dataset_info.json
index f0ee130c..06224a32 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -54,7 +54,8 @@
   },
   "alpaca_en": {
     "hf_hub_url": "llamafactory/alpaca_en",
-    "ms_hub_url": "llamafactory/alpaca_en"
+    "ms_hub_url": "llamafactory/alpaca_en",
+    "om_hub_url": "HaM/alpaca_en"
   },
   "alpaca_zh": {
     "hf_hub_url": "llamafactory/alpaca_zh",
@@ -66,7 +67,8 @@
   },
   "alpaca_gpt4_zh": {
     "hf_hub_url": "llamafactory/alpaca_gpt4_zh",
-    "ms_hub_url": "llamafactory/alpaca_gpt4_zh"
+    "ms_hub_url": "llamafactory/alpaca_gpt4_zh",
+    "om_hub_url": "State_Cloud/alpaca-gpt4-data-zh"
   },
   "glaive_toolcall_en": {
     "hf_hub_url": "llamafactory/glaive_toolcall_en",
diff --git a/src/llamafactory/data/loader.py b/src/llamafactory/data/loader.py
index 03a38fa8..0849b603 100644
--- a/src/llamafactory/data/loader.py
+++ b/src/llamafactory/data/loader.py
@@ -94,7 +94,7 @@ def _load_single_dataset(
                 name=data_name,
                 data_dir=data_dir,
                 data_files=data_files,
-                split=data_args.split,
+                split=dataset_attr.split,
                 cache_dir=cache_dir,
                 token=model_args.ms_hub_token,
                 streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
diff --git a/src/llamafactory/data/parser.py b/src/llamafactory/data/parser.py
index 696cd488..879264bb 100644
--- a/src/llamafactory/data/parser.py
+++ b/src/llamafactory/data/parser.py
@@ -98,6 +98,7 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
     dataset_list: List["DatasetAttr"] = []
     for name in dataset_names:
         if dataset_info is None: # dataset_dir is ONLINE
+            load_from = None
             if use_openmind():
                 load_from = "om_hub"
             if use_modelscope():
diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py
index 7ed20c2b..bf2386f4 100644
--- a/src/llamafactory/extras/constants.py
+++ b/src/llamafactory/extras/constants.py
@@ -107,6 +107,7 @@ VISION_MODELS = set()
 class DownloadSource(str, Enum):
     DEFAULT = "hf"
     MODELSCOPE = "ms"
+    MODELERS = "om"
 
 
 def register_model_group(
@@ -163,14 +164,17 @@ register_model_group(
         "Baichuan2-13B-Base": {
             DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-13B-Base",
             DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-13B-Base",
+            DownloadSource.MODELERS: "Baichuan/Baichuan2_13b_base_pt"
         },
         "Baichuan2-7B-Chat": {
             DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-7B-Chat",
             DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-7B-Chat",
+            DownloadSource.MODELERS: "Baichuan/Baichuan2_7b_chat_pt"
         },
         "Baichuan2-13B-Chat": {
             DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-13B-Chat",
             DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-13B-Chat",
+            DownloadSource.MODELERS: "Baichuan/Baichuan2_13b_chat_pt"
         },
     },
     template="baichuan2",
@@ -559,6 +563,7 @@ register_model_group(
         "Gemma-2-9B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-9b-it",
             DownloadSource.MODELSCOPE: "LLM-Research/gemma-2-9b-it",
+            DownloadSource.MODELERS: "LlamaFactory/Qwen2-VL-2B-Instruct"
         },
         "Gemma-2-27B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-27b-it",
@@ -656,6 +661,7 @@ register_model_group(
         "InternLM2.5-20B-Chat": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-20b-chat",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-20b-chat",
+            DownloadSource.MODELERS: "Intern/internlm2_5-20b-chat"
         },
     },
     template="intern2",
@@ -756,6 +762,7 @@ register_model_group(
         "Llama-3-8B-Chinese-Chat": {
             DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat",
+            DownloadSource.MODELERS: "HaM/Llama3-8B-Chinese-Chat",
         },
         "Llama-3-70B-Chinese-Chat": {
             DownloadSource.DEFAULT: "shenzhi-wang/Llama3-70B-Chinese-Chat",
@@ -960,6 +967,7 @@ register_model_group(
         "MiniCPM3-4B-Chat": {
             DownloadSource.DEFAULT: "openbmb/MiniCPM3-4B",
             DownloadSource.MODELSCOPE: "OpenBMB/MiniCPM3-4B",
+            DownloadSource.MODELERS: "LlamaFactory/MiniCPM3-4B"
         },
     },
     template="cpm3",
@@ -1699,6 +1707,7 @@ register_model_group(
         "Qwen2-VL-2B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct",
+            DownloadSource.MODELERS: "LlamaFactory/Qwen2-VL-2B-Instruct"
         },
         "Qwen2-VL-7B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct",
@@ -1801,10 +1810,12 @@ register_model_group(
         "TeleChat-7B-Chat": {
             DownloadSource.DEFAULT: "Tele-AI/telechat-7B",
             DownloadSource.MODELSCOPE: "TeleAI/telechat-7B",
+            DownloadSource.MODELERS: "TeleAI/TeleChat-7B-pt"
         },
         "TeleChat-12B-Chat": {
             DownloadSource.DEFAULT: "Tele-AI/TeleChat-12B",
             DownloadSource.MODELSCOPE: "TeleAI/TeleChat-12B",
+            DownloadSource.MODELERS: "TeleAI/TeleChat-12B-pt",
         },
         "TeleChat-12B-v2-Chat": {
             DownloadSource.DEFAULT: "Tele-AI/TeleChat-12B-v2",
@@ -2023,6 +2034,7 @@ register_model_group(
         "Yi-1.5-6B-Chat": {
             DownloadSource.DEFAULT: "01-ai/Yi-1.5-6B-Chat",
             DownloadSource.MODELSCOPE: "01ai/Yi-1.5-6B-Chat",
+            DownloadSource.MODELERS: "LlamaFactory/Yi-1.5-6B-Chat"
         },
         "Yi-1.5-9B-Chat": {
             DownloadSource.DEFAULT: "01-ai/Yi-1.5-9B-Chat",
diff --git a/src/llamafactory/webui/common.py b/src/llamafactory/webui/common.py
index d4e9be51..a078c976 100644
--- a/src/llamafactory/webui/common.py
+++ b/src/llamafactory/webui/common.py
@@ -31,7 +31,7 @@ from ..extras.constants import (
     DownloadSource,
 )
 from ..extras.logging import get_logger
-from ..extras.misc import use_modelscope
+from ..extras.misc import use_modelscope, use_openmind
 from ..extras.packages import is_gradio_available
 
 
@@ -112,6 +112,13 @@ def get_model_path(model_name: str) -> str:
     ):  # replace path
         model_path = path_dict.get(DownloadSource.MODELSCOPE)
 
+    if (
+        use_openmind()
+        and path_dict.get(DownloadSource.MODELERS)
+        and model_path == path_dict.get(DownloadSource.DEFAULT)
+    ):  # replace path
+        model_path = path_dict.get(DownloadSource.MODELERS)
+
     return model_path
 
 

From e8e98bb125bbbe551ea6622af199cf045bb44ed3 Mon Sep 17 00:00:00 2001
From: huniu20 <huniumail@gmail.com>
Date: Thu, 10 Oct 2024 17:16:46 +0800
Subject: [PATCH 3/8] add om_hub_token argument

Former-commit-id: 7b91be33c9cd8473453716f0c4c6dec924304efc
---
 src/llamafactory/data/loader.py        | 2 +-
 src/llamafactory/extras/constants.py   | 2 +-
 src/llamafactory/hparams/model_args.py | 4 ++++
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/src/llamafactory/data/loader.py b/src/llamafactory/data/loader.py
index 0849b603..385909fc 100644
--- a/src/llamafactory/data/loader.py
+++ b/src/llamafactory/data/loader.py
@@ -96,7 +96,7 @@ def _load_single_dataset(
                 data_files=data_files,
                 split=dataset_attr.split,
                 cache_dir=cache_dir,
-                token=model_args.ms_hub_token,
+                token=model_args.om_hub_token,
                 streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
             )
         except ImportError:
diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py
index bf2386f4..f0f6d619 100644
--- a/src/llamafactory/extras/constants.py
+++ b/src/llamafactory/extras/constants.py
@@ -563,7 +563,7 @@ register_model_group(
         "Gemma-2-9B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-9b-it",
             DownloadSource.MODELSCOPE: "LLM-Research/gemma-2-9b-it",
-            DownloadSource.MODELERS: "LlamaFactory/Qwen2-VL-2B-Instruct"
+            DownloadSource.MODELERS: "LlamaFactory/gemma-2-2b-it"
         },
         "Gemma-2-27B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-27b-it",
diff --git a/src/llamafactory/hparams/model_args.py b/src/llamafactory/hparams/model_args.py
index cd2f1867..9847d707 100644
--- a/src/llamafactory/hparams/model_args.py
+++ b/src/llamafactory/hparams/model_args.py
@@ -267,6 +267,10 @@ class ModelArguments(QuantizationArguments, ProcessorArguments, ExportArguments,
         default=None,
         metadata={"help": "Auth token to log in with ModelScope Hub."},
     )
+    om_hub_token: Optional[str] = field(
+        default=None,
+        metadata={"help": "Auth token to log in with Modelers Hub."},
+    )
     print_param_status: bool = field(
         default=False,
         metadata={"help": "For debugging purposes, print the status of the parameters in the model."},

From 39929bda5ab2d4132a6d28225c82b68b9179120e Mon Sep 17 00:00:00 2001
From: Johnny <johnnync13@gmail.com>
Date: Fri, 11 Oct 2024 12:29:09 +0200
Subject: [PATCH 4/8] Update setup.py

Former-commit-id: cb56673675a9d2ba359dd6d9a561084b9bad7bfd
---
 setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index f42cf7d1..4dca42af 100644
--- a/setup.py
+++ b/setup.py
@@ -54,7 +54,7 @@ extra_require = {
     "gptq": ["optimum>=1.17.0", "auto-gptq>=0.5.0"],
     "awq": ["autoawq"],
     "aqlm": ["aqlm[gpu]>=1.1.0"],
-    "vllm": ["vllm>=0.4.3,<=0.6.2"],
+    "vllm": ["vllm>=0.4.3,<=0.6.3"],
     "galore": ["galore-torch"],
     "badam": ["badam>=1.2.1"],
     "adam-mini": ["adam-mini"],

From 27be1e21226f5305c04a320dc284fe43076ef66a Mon Sep 17 00:00:00 2001
From: Johnny <johnnync13@gmail.com>
Date: Fri, 11 Oct 2024 12:29:33 +0200
Subject: [PATCH 5/8] Update parser.py

Former-commit-id: e5849cdcce109e15547edcf9a692e7c13d625e5a
---
 src/llamafactory/hparams/parser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llamafactory/hparams/parser.py b/src/llamafactory/hparams/parser.py
index 68a5d2f6..f9c6bfe8 100644
--- a/src/llamafactory/hparams/parser.py
+++ b/src/llamafactory/hparams/parser.py
@@ -123,7 +123,7 @@ def _check_extra_dependencies(
         require_version("mixture-of-depth>=1.1.6", "To fix: pip install mixture-of-depth>=1.1.6")
 
     if model_args.infer_backend == "vllm":
-        require_version("vllm>=0.4.3,<=0.6.2", "To fix: pip install vllm>=0.4.3,<=0.6.2")
+        require_version("vllm>=0.4.3,<=0.6.3", "To fix: pip install vllm>=0.4.3,<=0.6.2")
 
     if finetuning_args.use_galore:
         require_version("galore_torch", "To fix: pip install galore_torch")

From 5a3280ebee82fb4ca60f352e07bc35fe9f2ae702 Mon Sep 17 00:00:00 2001
From: huniu20 <huniumail@gmail.com>
Date: Fri, 11 Oct 2024 19:56:13 +0800
Subject: [PATCH 6/8] bugs fixed

Former-commit-id: 843b5d85e98b312e5d41ce62ec10e199011beb8c
---
 src/llamafactory/data/parser.py | 9 ++++-----
 src/llamafactory/extras/misc.py | 4 +---
 2 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/src/llamafactory/data/parser.py b/src/llamafactory/data/parser.py
index 879264bb..92cb7cbb 100644
--- a/src/llamafactory/data/parser.py
+++ b/src/llamafactory/data/parser.py
@@ -98,12 +98,11 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
     dataset_list: List["DatasetAttr"] = []
     for name in dataset_names:
         if dataset_info is None: # dataset_dir is ONLINE
-            load_from = None
             if use_openmind():
                 load_from = "om_hub"
-            if use_modelscope():
+            elif use_modelscope():
                 load_from = "ms_hub"
-            if load_from is None:
+            else:
                 load_from = "hf_hub"
             dataset_attr = DatasetAttr(load_from, dataset_name=name)
             dataset_list.append(dataset_attr)
@@ -117,9 +116,9 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
         has_ms_url = "ms_hub_url" in dataset_info[name]
 
         if has_om_url or has_hf_url or has_ms_url:
-            if (use_openmind() and has_om_url) or (not has_hf_url):
+            if has_om_url and (use_openmind() or not has_hf_url):
                 dataset_attr = DatasetAttr("om_hub", dataset_name=dataset_info[name]["om_hub_url"])
-            elif (use_modelscope() and has_ms_url) or (not has_hf_url):
+            if has_ms_url and (use_modelscope() or not has_hf_url):
                 dataset_attr = DatasetAttr("ms_hub", dataset_name=dataset_info[name]["ms_hub_url"])
             else:
                 dataset_attr = DatasetAttr("hf_hub", dataset_name=dataset_info[name]["hf_hub_url"])
diff --git a/src/llamafactory/extras/misc.py b/src/llamafactory/extras/misc.py
index 4c42900d..d4f1b152 100644
--- a/src/llamafactory/extras/misc.py
+++ b/src/llamafactory/extras/misc.py
@@ -237,11 +237,9 @@ def try_download_model_from_other_hub(model_args: "ModelArguments") -> str:
 
     if use_openmind():
         try:
-            import openmind
             from openmind.utils.hub import snapshot_download
 
-            revision = "main" if model_args.model_revision == "main" else model_args.model_revision
-            return snapshot_download(model_args.model_name_or_path, revision=revision, cache_dir=model_args.cache_dir)
+            return snapshot_download(model_args.model_name_or_path, revision=model_args.model_revision, cache_dir=model_args.cache_dir)
         except ImportError:
             raise ImportError("Please install openmind and openmind_hub via `pip install openmind -U`")
 

From e90a1199dac789c61f20606471e974a440957b29 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Fri, 11 Oct 2024 23:51:54 +0800
Subject: [PATCH 7/8] tiny fix

Former-commit-id: 3af57795dda5d236200bad4aa3f2e29ae8930fe2
---
 README.md                             |  6 ++--
 README_zh.md                          |  7 +++--
 docker/docker-cuda/docker-compose.yml |  1 +
 docker/docker-npu/docker-compose.yml  |  1 +
 docker/docker-rocm/docker-compose.yml |  1 +
 setup.py                              |  1 +
 src/llamafactory/data/loader.py       | 38 ++++++++++++-------------
 src/llamafactory/data/parser.py       | 20 +++++++-------
 src/llamafactory/extras/constants.py  | 35 +++++++++++++++--------
 src/llamafactory/extras/misc.py       | 40 +++++++++++++++------------
 src/llamafactory/hparams/parser.py    |  2 +-
 src/llamafactory/webui/common.py      |  8 +++---
 12 files changed, 91 insertions(+), 69 deletions(-)

diff --git a/README.md b/README.md
index 621a1c21..1705fef1 100644
--- a/README.md
+++ b/README.md
@@ -75,7 +75,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 ## Changelog
 
-[24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)** for Chinese mainland users. See [this tutorial](#download-from-modelers-hub) for usage.
+[24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)**. See [this tutorial](#download-from-modelers-hub) for usage.
 
 [24/09/19] We support fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models.
 
@@ -135,7 +135,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 [23/12/12] We supported fine-tuning the latest MoE model **[Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)** in our framework. See hardware requirement [here](#hardware-requirement).
 
-[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)** for Chinese mainland users. See [this tutorial](#download-from-modelscope-hub) for usage.
+[23/12/01] We supported downloading pre-trained models and datasets from the **[ModelScope Hub](https://modelscope.cn/models)**. See [this tutorial](#download-from-modelscope-hub) for usage.
 
 [23/10/21] We supported **[NEFTune](https://arxiv.org/abs/2310.05914)** trick for fine-tuning. Try `neftune_noise_alpha: 5` argument to activate NEFTune.
 
@@ -365,7 +365,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
 
-Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, quality, openmind
+Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, galore, badam, adam-mini, qwen, modelscope, openmind, quality
 
 > [!TIP]
 > Use `pip install --no-deps -e .` to resolve package conflicts.
diff --git a/README_zh.md b/README_zh.md
index 1d18ad16..b1810b59 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -75,6 +75,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 </details>
 
 ## 更新日志
+
 [24/10/09] 我们支持了从 **[魔乐社区](https://modelers.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔乐社区下载)。
 
 [24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。
@@ -365,7 +366,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
 
-可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality、openmind
+可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、openmind、quality
 
 > [!TIP]
 > 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
@@ -418,6 +419,7 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 ### 数据准备
 
 关于数据集文件的格式，请参考 [data/README_zh.md](data/README_zh.md) 的内容。你可以使用 HuggingFace / ModelScope / Modelers 上的数据集或加载本地数据集。
+
 > [!NOTE]
 > 使用自定义数据集时，请更新 `data/dataset_info.json` 文件。
 
@@ -591,7 +593,7 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1`
 
 ### 从魔乐社区下载
 
-您也可以通过下述方法使用魔乐社区，在魔乐社区上下载数据集和模型。
+您也可以通过下述方法，使用魔乐社区下载数据集和模型。
 
 ```bash
 export USE_OPENMIND_HUB=1 # Windows 使用 `set USE_OPENMIND_HUB=1`
@@ -599,7 +601,6 @@ export USE_OPENMIND_HUB=1 # Windows 使用 `set USE_OPENMIND_HUB=1`
 
 将 `model_name_or_path` 设置为模型 ID 来加载对应的模型。在[魔乐社区](https://modelers.cn/models)查看所有可用的模型，例如 `TeleAI/TeleChat-7B-pt`。
 
-
 ### 使用 W&B 面板
 
 若要使用 [Weights & Biases](https://wandb.ai) 记录实验数据，请在 yaml 文件中添加下面的参数。
diff --git a/docker/docker-cuda/docker-compose.yml b/docker/docker-cuda/docker-compose.yml
index 7af06b74..82e05b36 100644
--- a/docker/docker-cuda/docker-compose.yml
+++ b/docker/docker-cuda/docker-compose.yml
@@ -16,6 +16,7 @@ services:
     volumes:
       - ../../hf_cache:/root/.cache/huggingface
       - ../../ms_cache:/root/.cache/modelscope
+      - ../../om_cache:/root/.cache/openmind
       - ../../data:/app/data
       - ../../output:/app/output
     ports:
diff --git a/docker/docker-npu/docker-compose.yml b/docker/docker-npu/docker-compose.yml
index 657cba9f..333f63ac 100644
--- a/docker/docker-npu/docker-compose.yml
+++ b/docker/docker-npu/docker-compose.yml
@@ -10,6 +10,7 @@ services:
     volumes:
       - ../../hf_cache:/root/.cache/huggingface
       - ../../ms_cache:/root/.cache/modelscope
+      - ../../om_cache:/root/.cache/openmind
       - ../../data:/app/data
       - ../../output:/app/output
       - /usr/local/dcmi:/usr/local/dcmi
diff --git a/docker/docker-rocm/docker-compose.yml b/docker/docker-rocm/docker-compose.yml
index 2a4ea960..c5b5d748 100644
--- a/docker/docker-rocm/docker-compose.yml
+++ b/docker/docker-rocm/docker-compose.yml
@@ -15,6 +15,7 @@ services:
     volumes:
       - ../../hf_cache:/root/.cache/huggingface
       - ../../ms_cache:/root/.cache/modelscope
+      - ../../om_cache:/root/.cache/openmind
       - ../../data:/app/data
       - ../../output:/app/output
       - ../../saves:/app/saves
diff --git a/setup.py b/setup.py
index 4dca42af..90f6362d 100644
--- a/setup.py
+++ b/setup.py
@@ -60,6 +60,7 @@ extra_require = {
     "adam-mini": ["adam-mini"],
     "qwen": ["transformers_stream_generator"],
     "modelscope": ["modelscope"],
+    "openmind": ["openmind"],
     "dev": ["ruff", "pytest"],
 }
 
diff --git a/src/llamafactory/data/loader.py b/src/llamafactory/data/loader.py
index 385909fc..95398e26 100644
--- a/src/llamafactory/data/loader.py
+++ b/src/llamafactory/data/loader.py
@@ -53,7 +53,7 @@ def _load_single_dataset(
     """
     logger.info("Loading dataset {}...".format(dataset_attr))
     data_path, data_name, data_dir, data_files = None, None, None, None
-    if dataset_attr.load_from in ["om_hub", "hf_hub", "ms_hub"]:
+    if dataset_attr.load_from in ["hf_hub", "ms_hub", "om_hub"]:
         data_path = dataset_attr.dataset_name
         data_name = dataset_attr.subset
         data_dir = dataset_attr.folder
@@ -84,24 +84,7 @@ def _load_single_dataset(
     else:
         raise NotImplementedError("Unknown load type: {}.".format(dataset_attr.load_from))
 
-    if dataset_attr.load_from == "om_hub":
-        try:
-            from openmind import OmDataset
-            from openmind.utils.hub import OM_DATASETS_CACHE
-            cache_dir = model_args.cache_dir or OM_DATASETS_CACHE
-            dataset = OmDataset.load_dataset(
-                path=data_path,
-                name=data_name,
-                data_dir=data_dir,
-                data_files=data_files,
-                split=dataset_attr.split,
-                cache_dir=cache_dir,
-                token=model_args.om_hub_token,
-                streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
-            )
-        except ImportError:
-            raise ImportError("Please install openmind via `pip install openmind -U`")
-    elif dataset_attr.load_from == "ms_hub":
+    if dataset_attr.load_from == "ms_hub":
         require_version("modelscope>=1.11.0", "To fix: pip install modelscope>=1.11.0")
         from modelscope import MsDataset
         from modelscope.utils.config_ds import MS_DATASETS_CACHE
@@ -119,6 +102,23 @@ def _load_single_dataset(
         )
         if isinstance(dataset, MsDataset):
             dataset = dataset.to_hf_dataset()
+
+    elif dataset_attr.load_from == "om_hub":
+        require_version("openmind>=0.8.0", "To fix: pip install openmind>=0.8.0")
+        from openmind import OmDataset
+        from openmind.utils.hub import OM_DATASETS_CACHE
+
+        cache_dir = model_args.cache_dir or OM_DATASETS_CACHE
+        dataset = OmDataset.load_dataset(
+            path=data_path,
+            name=data_name,
+            data_dir=data_dir,
+            data_files=data_files,
+            split=dataset_attr.split,
+            cache_dir=cache_dir,
+            token=model_args.om_hub_token,
+            streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
+        )
     else:
         dataset = load_dataset(
             path=data_path,
diff --git a/src/llamafactory/data/parser.py b/src/llamafactory/data/parser.py
index 92cb7cbb..b9060425 100644
--- a/src/llamafactory/data/parser.py
+++ b/src/llamafactory/data/parser.py
@@ -20,7 +20,7 @@ from typing import Any, Dict, List, Literal, Optional, Sequence
 from transformers.utils import cached_file
 
 from ..extras.constants import DATA_CONFIG
-from ..extras.misc import use_openmind, use_modelscope
+from ..extras.misc import use_modelscope, use_openmind
 
 
 @dataclass
@@ -30,7 +30,7 @@ class DatasetAttr:
     """
 
     # basic configs
-    load_from: Literal["hf_hub", "ms_hub", "script", "file"]
+    load_from: Literal["hf_hub", "ms_hub", "om_hub", "script", "file"]
     dataset_name: str
     formatting: Literal["alpaca", "sharegpt"] = "alpaca"
     ranking: bool = False
@@ -97,11 +97,11 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
 
     dataset_list: List["DatasetAttr"] = []
     for name in dataset_names:
-        if dataset_info is None: # dataset_dir is ONLINE
-            if use_openmind():
-                load_from = "om_hub"
-            elif use_modelscope():
+        if dataset_info is None:  # dataset_dir is ONLINE
+            if use_modelscope():
                 load_from = "ms_hub"
+            elif use_openmind():
+                load_from = "om_hub"
             else:
                 load_from = "hf_hub"
             dataset_attr = DatasetAttr(load_from, dataset_name=name)
@@ -111,15 +111,15 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
         if name not in dataset_info:
             raise ValueError("Undefined dataset {} in {}.".format(name, DATA_CONFIG))
 
-        has_om_url = "om_hub_url" in dataset_info[name]
         has_hf_url = "hf_hub_url" in dataset_info[name]
         has_ms_url = "ms_hub_url" in dataset_info[name]
+        has_om_url = "om_hub_url" in dataset_info[name]
 
-        if has_om_url or has_hf_url or has_ms_url:
-            if has_om_url and (use_openmind() or not has_hf_url):
-                dataset_attr = DatasetAttr("om_hub", dataset_name=dataset_info[name]["om_hub_url"])
+        if has_hf_url or has_ms_url or has_om_url:
             if has_ms_url and (use_modelscope() or not has_hf_url):
                 dataset_attr = DatasetAttr("ms_hub", dataset_name=dataset_info[name]["ms_hub_url"])
+            elif has_om_url and (use_openmind() or not has_hf_url):
+                dataset_attr = DatasetAttr("om_hub", dataset_name=dataset_info[name]["om_hub_url"])
             else:
                 dataset_attr = DatasetAttr("hf_hub", dataset_name=dataset_info[name]["hf_hub_url"])
         elif "script_url" in dataset_info[name]:
diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py
index f0f6d619..c6ddd61b 100644
--- a/src/llamafactory/extras/constants.py
+++ b/src/llamafactory/extras/constants.py
@@ -107,7 +107,7 @@ VISION_MODELS = set()
 class DownloadSource(str, Enum):
     DEFAULT = "hf"
     MODELSCOPE = "ms"
-    MODELERS = "om"
+    OPENMIND = "om"
 
 
 def register_model_group(
@@ -164,17 +164,17 @@ register_model_group(
         "Baichuan2-13B-Base": {
             DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-13B-Base",
             DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-13B-Base",
-            DownloadSource.MODELERS: "Baichuan/Baichuan2_13b_base_pt"
+            DownloadSource.OPENMIND: "Baichuan/Baichuan2_13b_base_pt",
         },
         "Baichuan2-7B-Chat": {
             DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-7B-Chat",
             DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-7B-Chat",
-            DownloadSource.MODELERS: "Baichuan/Baichuan2_7b_chat_pt"
+            DownloadSource.OPENMIND: "Baichuan/Baichuan2_7b_chat_pt",
         },
         "Baichuan2-13B-Chat": {
             DownloadSource.DEFAULT: "baichuan-inc/Baichuan2-13B-Chat",
             DownloadSource.MODELSCOPE: "baichuan-inc/Baichuan2-13B-Chat",
-            DownloadSource.MODELERS: "Baichuan/Baichuan2_13b_chat_pt"
+            DownloadSource.OPENMIND: "Baichuan/Baichuan2_13b_chat_pt",
         },
     },
     template="baichuan2",
@@ -559,11 +559,12 @@ register_model_group(
         "Gemma-2-2B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-2b-it",
             DownloadSource.MODELSCOPE: "LLM-Research/gemma-2-2b-it",
+            DownloadSource.OPENMIND: "LlamaFactory/gemma-2-2b-it",
         },
         "Gemma-2-9B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-9b-it",
             DownloadSource.MODELSCOPE: "LLM-Research/gemma-2-9b-it",
-            DownloadSource.MODELERS: "LlamaFactory/gemma-2-2b-it"
+            DownloadSource.OPENMIND: "LlamaFactory/gemma-2-9b-it",
         },
         "Gemma-2-27B-Instruct": {
             DownloadSource.DEFAULT: "google/gemma-2-27b-it",
@@ -583,6 +584,7 @@ register_model_group(
         "GLM-4-9B-Chat": {
             DownloadSource.DEFAULT: "THUDM/glm-4-9b-chat",
             DownloadSource.MODELSCOPE: "ZhipuAI/glm-4-9b-chat",
+            DownloadSource.OPENMIND: "LlamaFactory/glm-4-9b-chat",
         },
         "GLM-4-9B-1M-Chat": {
             DownloadSource.DEFAULT: "THUDM/glm-4-9b-chat-1m",
@@ -637,6 +639,7 @@ register_model_group(
         "InternLM2.5-1.8B": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-1_8b",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-1_8b",
+            DownloadSource.OPENMIND: "Intern/internlm2_5-1_8b",
         },
         "InternLM2.5-7B": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-7b",
@@ -645,23 +648,27 @@ register_model_group(
         "InternLM2.5-20B": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-20b",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-20b",
+            DownloadSource.OPENMIND: "Intern/internlm2_5-20b",
         },
         "InternLM2.5-1.8B-Chat": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-1_8b-chat",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-1_8b-chat",
+            DownloadSource.OPENMIND: "Intern/internlm2_5-1_8b-chat",
         },
         "InternLM2.5-7B-Chat": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-7b-chat",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-7b-chat",
+            DownloadSource.OPENMIND: "Intern/internlm2_5-7b-chat",
         },
         "InternLM2.5-7B-1M-Chat": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-7b-chat-1m",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-7b-chat-1m",
+            DownloadSource.OPENMIND: "Intern/internlm2_5-7b-chat-1m",
         },
         "InternLM2.5-20B-Chat": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-20b-chat",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-20b-chat",
-            DownloadSource.MODELERS: "Intern/internlm2_5-20b-chat"
+            DownloadSource.OPENMIND: "Intern/internlm2_5-20b-chat",
         },
     },
     template="intern2",
@@ -762,7 +769,7 @@ register_model_group(
         "Llama-3-8B-Chinese-Chat": {
             DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat",
-            DownloadSource.MODELERS: "HaM/Llama3-8B-Chinese-Chat",
+            DownloadSource.OPENMIND: "LlamaFactory/Llama3-Chinese-8B-Instruct",
         },
         "Llama-3-70B-Chinese-Chat": {
             DownloadSource.DEFAULT: "shenzhi-wang/Llama3-70B-Chinese-Chat",
@@ -967,7 +974,7 @@ register_model_group(
         "MiniCPM3-4B-Chat": {
             DownloadSource.DEFAULT: "openbmb/MiniCPM3-4B",
             DownloadSource.MODELSCOPE: "OpenBMB/MiniCPM3-4B",
-            DownloadSource.MODELERS: "LlamaFactory/MiniCPM3-4B"
+            DownloadSource.OPENMIND: "LlamaFactory/MiniCPM3-4B",
         },
     },
     template="cpm3",
@@ -1417,14 +1424,17 @@ register_model_group(
         "Qwen2-0.5B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-0.5B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-0.5B-Instruct",
+            DownloadSource.OPENMIND: "LlamaFactory/Qwen2-0.5B-Instruct",
         },
         "Qwen2-1.5B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-1.5B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-1.5B-Instruct",
+            DownloadSource.OPENMIND: "LlamaFactory/Qwen2-1.5B-Instruct",
         },
         "Qwen2-7B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-7B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-7B-Instruct",
+            DownloadSource.OPENMIND: "LlamaFactory/Qwen2-7B-Instruct",
         },
         "Qwen2-72B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-72B-Instruct",
@@ -1707,11 +1717,12 @@ register_model_group(
         "Qwen2-VL-2B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct",
-            DownloadSource.MODELERS: "LlamaFactory/Qwen2-VL-2B-Instruct"
+            DownloadSource.OPENMIND: "LlamaFactory/Qwen2-VL-2B-Instruct",
         },
         "Qwen2-VL-7B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-7B-Instruct",
+            DownloadSource.OPENMIND: "LlamaFactory/Qwen2-VL-7B-Instruct",
         },
         "Qwen2-VL-72B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-72B-Instruct",
@@ -1810,12 +1821,12 @@ register_model_group(
         "TeleChat-7B-Chat": {
             DownloadSource.DEFAULT: "Tele-AI/telechat-7B",
             DownloadSource.MODELSCOPE: "TeleAI/telechat-7B",
-            DownloadSource.MODELERS: "TeleAI/TeleChat-7B-pt"
+            DownloadSource.OPENMIND: "TeleAI/TeleChat-7B-pt",
         },
         "TeleChat-12B-Chat": {
             DownloadSource.DEFAULT: "Tele-AI/TeleChat-12B",
             DownloadSource.MODELSCOPE: "TeleAI/TeleChat-12B",
-            DownloadSource.MODELERS: "TeleAI/TeleChat-12B-pt",
+            DownloadSource.OPENMIND: "TeleAI/TeleChat-12B-pt",
         },
         "TeleChat-12B-v2-Chat": {
             DownloadSource.DEFAULT: "Tele-AI/TeleChat-12B-v2",
@@ -2034,7 +2045,7 @@ register_model_group(
         "Yi-1.5-6B-Chat": {
             DownloadSource.DEFAULT: "01-ai/Yi-1.5-6B-Chat",
             DownloadSource.MODELSCOPE: "01ai/Yi-1.5-6B-Chat",
-            DownloadSource.MODELERS: "LlamaFactory/Yi-1.5-6B-Chat"
+            DownloadSource.OPENMIND: "LlamaFactory/Yi-1.5-6B-Chat",
         },
         "Yi-1.5-9B-Chat": {
             DownloadSource.DEFAULT: "01-ai/Yi-1.5-9B-Chat",
diff --git a/src/llamafactory/extras/misc.py b/src/llamafactory/extras/misc.py
index d4f1b152..fd78530a 100644
--- a/src/llamafactory/extras/misc.py
+++ b/src/llamafactory/extras/misc.py
@@ -232,28 +232,34 @@ def torch_gc() -> None:
 
 
 def try_download_model_from_other_hub(model_args: "ModelArguments") -> str:
-    if (not use_openmind() and not use_modelscope()) or os.path.exists(model_args.model_name_or_path):
+    if (not use_modelscope() and not use_openmind()) or os.path.exists(model_args.model_name_or_path):
         return model_args.model_name_or_path
 
-    if use_openmind():
-        try:
-            from openmind.utils.hub import snapshot_download
-
-            return snapshot_download(model_args.model_name_or_path, revision=model_args.model_revision, cache_dir=model_args.cache_dir)
-        except ImportError:
-            raise ImportError("Please install openmind and openmind_hub via `pip install openmind -U`")
-
     if use_modelscope():
-        try:
-            from modelscope import snapshot_download
+        require_version("modelscope>=1.11.0", "To fix: pip install modelscope>=1.11.0")
+        from modelscope import snapshot_download
 
-            revision = "master" if model_args.model_revision == "main" else model_args.model_revision
-            return snapshot_download(model_args.model_name_or_path, revision=revision, cache_dir=model_args.cache_dir)
-        except ImportError:
-            raise ImportError("Please install modelscope via `pip install modelscope -U`")
+        revision = "master" if model_args.model_revision == "main" else model_args.model_revision
+        return snapshot_download(
+            model_args.model_name_or_path,
+            revision=revision,
+            cache_dir=model_args.cache_dir,
+        )
+
+    if use_openmind():
+        require_version("openmind>=0.8.0", "To fix: pip install openmind>=0.8.0")
+        from openmind.utils.hub import snapshot_download
+
+        return snapshot_download(
+            model_args.model_name_or_path,
+            revision=model_args.model_revision,
+            cache_dir=model_args.cache_dir,
+        )
 
-def use_openmind() -> bool:
-    return os.environ.get("USE_OPENMIND_HUB", "0").lower() in ["true", "1"]
 
 def use_modelscope() -> bool:
     return os.environ.get("USE_MODELSCOPE_HUB", "0").lower() in ["true", "1"]
+
+
+def use_openmind() -> bool:
+    return os.environ.get("USE_OPENMIND_HUB", "0").lower() in ["true", "1"]
diff --git a/src/llamafactory/hparams/parser.py b/src/llamafactory/hparams/parser.py
index f9c6bfe8..f62468a4 100644
--- a/src/llamafactory/hparams/parser.py
+++ b/src/llamafactory/hparams/parser.py
@@ -123,7 +123,7 @@ def _check_extra_dependencies(
         require_version("mixture-of-depth>=1.1.6", "To fix: pip install mixture-of-depth>=1.1.6")
 
     if model_args.infer_backend == "vllm":
-        require_version("vllm>=0.4.3,<=0.6.3", "To fix: pip install vllm>=0.4.3,<=0.6.2")
+        require_version("vllm>=0.4.3,<=0.6.3", "To fix: pip install vllm>=0.4.3,<=0.6.3")
 
     if finetuning_args.use_galore:
         require_version("galore_torch", "To fix: pip install galore_torch")
diff --git a/src/llamafactory/webui/common.py b/src/llamafactory/webui/common.py
index a078c976..b28626bc 100644
--- a/src/llamafactory/webui/common.py
+++ b/src/llamafactory/webui/common.py
@@ -109,15 +109,15 @@ def get_model_path(model_name: str) -> str:
         use_modelscope()
         and path_dict.get(DownloadSource.MODELSCOPE)
         and model_path == path_dict.get(DownloadSource.DEFAULT)
-    ):  # replace path
+    ):  # replace hf path with ms path
         model_path = path_dict.get(DownloadSource.MODELSCOPE)
 
     if (
         use_openmind()
-        and path_dict.get(DownloadSource.MODELERS)
+        and path_dict.get(DownloadSource.OPENMIND)
         and model_path == path_dict.get(DownloadSource.DEFAULT)
-    ):  # replace path
-        model_path = path_dict.get(DownloadSource.MODELERS)
+    ):  # replace hf path with om path
+        model_path = path_dict.get(DownloadSource.OPENMIND)
 
     return model_path
 

From 92de7261027326b4d86abe6b88d7060782f1b0d6 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Sat, 12 Oct 2024 01:24:43 +0800
Subject: [PATCH 8/8] fix #5668

Former-commit-id: 40ceba500bab7452b8671a9fbcd14bbf4a8f6f37
---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 69489bec..d26961f7 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,7 +3,7 @@ datasets>=2.16.0,<=2.21.0
 accelerate>=0.30.1,<=0.34.2
 peft>=0.11.1,<=0.12.0
 trl>=0.8.6,<=0.9.6
-gradio>=4.0.0
+gradio>=4.0.0,<5.0.0
 pandas>=2.0.0
 scipy
 einops