apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

chat_to_str for chat-history related dataset

Browse source
This commit is contained in:
51616 2025-08-28 05:17:31 +00:00
parent 7ac74e6d58
commit 1193d10fb4
1 changed files with 12 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

13
src/ctx_to_lora/data/preprocessing_fn.py
View file

@ -14,6 +14,17 @@ def closed_qa_prompting(prompt: str):
return template.format(input=prompt)
def chat_to_str(messages: list[dict[str, str]]):
return "\n\n".join(
[
"Message from: {role}\n{content}".format(
**{**m, "role": m["role"].capitalize()}
)
for m in messages
]
)
def get_preprocessing_fn(
ds_name: str,
is_eval: bool,
@ -266,7 +277,7 @@ def get_preprocessing_fn(
# ctx → all history up to the last turn
# q → last user input
def f(sample):
chat_history = sample["messages"][:-2]
chat_history = chat_to_str(sample["messages"][:-2])
q = sample["messages"][-2]["content"]
response = sample["messages"][-1]["content"]
return {"context": chat_history, "prompt": q, "response": response}