Skip to content

[colossalqa] fix pangu api #5170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MichelleMa8 merged 2 commits into from
Dec 11, 2023
Merged

[colossalqa] fix pangu api #5170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
63c4a73
fix pangu api
MichelleMa8 Dec 7, 2023
a88eb46
add comment
MichelleMa8 Dec 11, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion applications/ColossalQA/colossalqa/memory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,7 @@ def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, str]:
remain = self.max_tokens - prompt_length
while self.get_conversation_length() > remain:
if len(self.buffered_history.messages) <= 2:
raise RuntimeError("Exeeed max_tokens, trunck size of retrieved documents is too large")
raise RuntimeError("Exceed max_tokens, trunk size of retrieved documents is too large")
temp = self.buffered_history.messages.pop(0)
self.summarized_history_temp.messages.append(temp)
temp = self.buffered_history.messages.pop(0)
Expand Down
12 changes: 8 additions & 4 deletions applications/ColossalQA/examples/webui_demo/server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,12 +77,16 @@ def generate(data: GenerationTaskReq, request: Request):
colossal_api = ColossalAPI(model_name, all_config["model"]["model_path"])
llm = ColossalLLM(n=1, api=colossal_api)
elif all_config["model"]["mode"] == "api":
all_config["chain"]["mem_llm_kwargs"] = None
all_config["chain"]["disambig_llm_kwargs"] = None
all_config["chain"]["gen_llm_kwargs"] = None
if model_name == "pangu_api":
from colossalqa.local.pangu_llm import Pangu
llm = Pangu(id=1)

gen_config = {
"user": "User",
"max_tokens": all_config["chain"]["disambig_llm_kwargs"]["max_new_tokens"],
"temperature": all_config["chain"]["disambig_llm_kwargs"]["temperature"],
"n": 1 # the number of responses generated
}
llm = Pangu(gen_config=gen_config)
llm.set_auth_config() # verify user's auth info here
elif model_name == "chatgpt_api":
from langchain.llms import OpenAI
Expand Down