github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-07 11:23:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(model): Support codegeex4-all-9b (#1720)

Browse Source
This commit is contained in:
Fangyin Cheng 2024-07-14 20:39:38 +08:00 committed by GitHub
parent 125db534cb
commit e4abd56eeb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 22 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dbgpt/configs/model_config.py
View File

@ -55,6 +55,8 @@ LLM_MODEL_CONFIG = {
# https://huggingface.co/THUDM/glm-4-9b-chat # https://huggingface.co/THUDM/glm-4-9b-chat
"glm-4-9b-chat": os.path.join(MODEL_PATH, "glm-4-9b-chat"), "glm-4-9b-chat": os.path.join(MODEL_PATH, "glm-4-9b-chat"),
"glm-4-9b-chat-1m": os.path.join(MODEL_PATH, "glm-4-9b-chat-1m"), "glm-4-9b-chat-1m": os.path.join(MODEL_PATH, "glm-4-9b-chat-1m"),
# https://huggingface.co/THUDM/codegeex4-all-9b
"codegeex4-all-9b": os.path.join(MODEL_PATH, "codegeex4-all-9b"),
"guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"), "guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"),
"falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"), "falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"),
"gorilla-7b": os.path.join(MODEL_PATH, "gorilla-7b"), "gorilla-7b": os.path.join(MODEL_PATH, "gorilla-7b"),

23
dbgpt/model/adapter/hf_adapter.py
View File

@ -552,9 +552,9 @@ class OpenChatAdapter(Llama3Adapter):
) )
class GLM4Aapter(NewHFChatModelAdapter): class GLM4Adapter(NewHFChatModelAdapter):
""" """
https://huggingface.co/defog/glm-4-8b https://huggingface.co/THUDM/glm-4-9b-chat
""" """
def do_match(self, lower_model_name_or_path: Optional[str] = None): def do_match(self, lower_model_name_or_path: Optional[str] = None):
@ -565,6 +565,22 @@ class GLM4Aapter(NewHFChatModelAdapter):
) )
class Codegeex4Adapter(GLM4Adapter):
"""
https://huggingface.co/THUDM/codegeex4-all-9b
"""
def do_match(self, lower_model_name_or_path: Optional[str] = None):
return lower_model_name_or_path and "codegeex4" in lower_model_name_or_path
def load(self, model_path: str, from_pretrained_kwargs: dict):
if not from_pretrained_kwargs:
from_pretrained_kwargs = {}
if "trust_remote_code" not in from_pretrained_kwargs:
from_pretrained_kwargs["trust_remote_code"] = True
return super().load(model_path, from_pretrained_kwargs)
# The following code is used to register the model adapter # The following code is used to register the model adapter
# The last registered model adapter is matched first # The last registered model adapter is matched first
register_model_adapter(YiAdapter) register_model_adapter(YiAdapter)
@ -583,5 +599,6 @@ register_model_adapter(SailorAdapter)
register_model_adapter(PhiAdapter) register_model_adapter(PhiAdapter)
register_model_adapter(SQLCoderAdapter) register_model_adapter(SQLCoderAdapter)
register_model_adapter(OpenChatAdapter) register_model_adapter(OpenChatAdapter)
register_model_adapter(GLM4Aapter) register_model_adapter(GLM4Adapter)
register_model_adapter(Codegeex4Adapter)
register_model_adapter(Qwen2Adapter) register_model_adapter(Qwen2Adapter)