github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-08-06 10:54:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

add other codellama models

Browse Source
This commit is contained in:
wangzaistone 2023-10-31 17:24:54 +08:00
parent 48539d7206
commit a670e5c00d
3 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
pilot/configs/model_config.py
View File

@ -78,8 +78,15 @@ LLM_MODEL_CONFIG = {
"internlm-7b": os.path.join(MODEL_PATH, "internlm-chat-7b"), "internlm-7b": os.path.join(MODEL_PATH, "internlm-chat-7b"),
"internlm-7b-8k": os.path.join(MODEL_PATH, "internlm-chat-7b-8k"), "internlm-7b-8k": os.path.join(MODEL_PATH, "internlm-chat-7b-8k"),
"internlm-20b": os.path.join(MODEL_PATH, "internlm-chat-20b"), "internlm-20b": os.path.join(MODEL_PATH, "internlm-chat-20b"),
"codellama-7b": os.path.join(MODEL_PATH, "CodeLlama-7b-Instruct-hf"),
"codellama-7b-sql-sft": os.path.join(MODEL_PATH, "codellama-7b-sql-sft"),
"codellama-13b": os.path.join(MODEL_PATH, "CodeLlama-13b-Instruct-hf"),
"codellama-13b-sql-sft": os.path.join(MODEL_PATH, "codellama-13b-sql-sft"), "codellama-13b-sql-sft": os.path.join(MODEL_PATH, "codellama-13b-sql-sft"),
# For test now # For test now
"opt-125m": os.path.join(MODEL_PATH, "opt-125m"), "opt-125m": os.path.join(MODEL_PATH, "opt-125m"),
} }

2
pilot/model/adapter.py
View File

@ -323,7 +323,7 @@ class CodeLlamaAdapter(BaseLLMAdaper):
"""The model adapter for codellama """ """The model adapter for codellama """
def match(self, model_path: str): def match(self, model_path: str):
return "codelama" in model_path.lower() return "codellama" in model_path.lower()
def loader(self, model_path: str, from_pretrained_kwargs: dict): def loader(self, model_path: str, from_pretrained_kwargs: dict):
model, tokenizer = super().loader(model_path, from_pretrained_kwargs) model, tokenizer = super().loader(model_path, from_pretrained_kwargs)

5
pilot/model/model_adapter.py
View File

@ -45,7 +45,10 @@ _OLD_MODELS = [
"llama-cpp", "llama-cpp",
"proxyllm", "proxyllm",
"gptj-6b", "gptj-6b",
"codellama-13b-sql-sft" "codellama-13b-sql-sft",
"codellama-7b",
"codellama-7b-sql-sft",
"codellama-13b"
] ]