mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-08-01 11:12:50 +08:00
tiny fix
Former-commit-id: 3af57795dda5d236200bad4aa3f2e29ae8930fe2
This commit is contained in:
parent
012f4fef6b
commit
e90a1199da
@ -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.
|
||||
|
@ -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。
|
||||
|
@ -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:
|
||||
|
@ -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
|
||||
|
@ -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
|
||||
|
1
setup.py
1
setup.py
@ -60,6 +60,7 @@ extra_require = {
|
||||
"adam-mini": ["adam-mini"],
|
||||
"qwen": ["transformers_stream_generator"],
|
||||
"modelscope": ["modelscope"],
|
||||
"openmind": ["openmind"],
|
||||
"dev": ["ruff", "pytest"],
|
||||
}
|
||||
|
||||
|
@ -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,
|
||||
|
@ -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]:
|
||||
|
@ -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",
|
||||
|
@ -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"]
|
||||
|
@ -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")
|
||||
|
@ -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
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user