unsloth/studio/backend/models
Roland Tannous 2fc50ff0cf refactor: advisor maps columns to roles instead of generating templates
The advisor now only assigns columns to user/assistant roles and
generates a system prompt. Templates (user_template, assistant_template)
are removed entirely — the LLM was frequently putting all columns in
user or copying actual data values into templates.

Column values are now used directly as message content, grouped and
concatenated by role. This is simpler, more robust, and prevents the
class of bugs where the advisor generates bad template content.
2026-03-10 17:17:27 +00:00
..
.gitkeep fix: restore models directory files deleted during restructure 2026-02-02 19:36:30 +00:00
__init__.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
auth.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
data_recipe.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
datasets.py refactor: advisor maps columns to roles instead of generating templates 2026-03-10 17:17:27 +00:00
export.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
inference.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
models.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
responses.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
training.py feat: Dataset Conversion Advisor — multi-pass LLM for non-conversational datasets 2026-03-10 15:39:56 +00:00
users.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00