-
Notifications
You must be signed in to change notification settings - Fork 71
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'main' of github.com:jondurbin/airoboros
- Loading branch information
Showing
2 changed files
with
86 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| import re | ||
| import json | ||
| import uuid | ||
| inputs = [json.loads(line) for line in open("instructions.jsonl").readlines()] | ||
|
|
||
| def split_response(instruction, response): | ||
| if '</s>' not in response: | ||
| return [ | ||
| { | ||
| "from": "human", | ||
| "value": instruction, | ||
| }, | ||
| { | ||
| "from": "gpt", | ||
| "value": response, | ||
| }, | ||
| ] | ||
| parts = response.split('</s>') | ||
| user = [instruction] | ||
| assistant = [] | ||
| for idx in range(len(parts)): | ||
| part = parts[idx] | ||
| if idx == 0: | ||
| assistant.append(part) | ||
| continue | ||
| match = re.match(r'^\s*USER:(.*?)ASSISTANT:(.*)\s*$', part, re.DOTALL) | ||
| if not match: | ||
| return None | ||
| user.append(match.group(1).strip()) | ||
| assistant.append(match.group(2).strip()) | ||
| conv = [] | ||
| for idx in range(len(user)): | ||
| conv.append({ | ||
| "from": "human", | ||
| "value": user[idx], | ||
| }) | ||
| conv.append({ | ||
| "from": "gpt", | ||
| "value": assistant[idx] | ||
| }) | ||
| return conv | ||
|
|
||
| conversations = [] | ||
| for row in inputs: | ||
| conversation = split_response(row['instruction'], row['response']) | ||
| if not conversation: | ||
| print("Bad format, skipping...") | ||
| continue | ||
| conversations.append({ | ||
| "id": str(uuid.uuid4()), | ||
| "conversations": conversation, | ||
| }) | ||
| with open("as_conversations.json", "w") as outfile: | ||
| outfile.write(json.dumps(conversations, indent=2)) |