ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/studio/backend/utils/datasets
History
Roland Tannous 3e3d221381 fix: improve advisor prompts for more reliable column role assignment 
- Pass 1: clearer definition of "conversational" vs non-conversational,
  constrained dataset_type to specific enum values
- Pass 2: much more explicit worked examples with step-by-step reasoning,
  added "skip" role for metadata columns, stronger reminder at end that
  all-user is wrong
- Pass 3: returns raw text instead of JSON for cleaner system prompts,
  removed system message to give model more freedom
2026-03-10 18:01:20 +00:00
..
__init__.py feat: add ShareGPT+image VLM format support and improve image column detection 2026-03-10 01:27:36 +00:00
chat_templates.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
data_collators.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
dataset_utils.py refactor: advisor maps columns to roles instead of generating templates 2026-03-10 17:17:27 +00:00
format_conversion.py feat: add LLM-assisted dataset detection using ephemeral GGUF helper 2026-03-10 09:20:45 +00:00
format_detection.py fix: probe image column candidates when multiple exist 2026-03-10 01:38:33 +00:00
llm_assist.py fix: improve advisor prompts for more reliable column role assignment 2026-03-10 18:01:20 +00:00
model_mappings.py Add AGPL-3.0 SPDX headers to all source files 2026-03-09 20:17:45 +00:00
vlm_processing.py debug: switch to print() for subprocess visibility 2026-03-10 12:49:01 +00:00