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

tiny fix

Browse Source 
Former-commit-id: 1fe424323b212094856f423351dc2a15774d39c3
This commit is contained in:
hiyouga
2024-10-11 23:51:54 +08:00
parent c71c78da50
commit c7efc7f2ed
12 changed files with 91 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
src/llamafactory/extras/constants.py
View File

@@ -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",

40
src/llamafactory/extras/misc.py
View File

@@ -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"]