[manus] Modular DPO Dataset Builder for MLX (#5) #6
Reference in New Issue
Block a user
Delete Branch "manus/dpo-data-pipeline"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Fixes #5
Sovereign Data Preparation
This PR implements a modular, rule-based DPO (Direct Preference Optimization) dataset builder, unblocking the training of Timmy's model on human preferences locally on Apple Silicon.
Key Contributions
training/build_dpo_pairs.py: A modular script (< 100 lines) that transforms curated chat history intoprompt,chosen, andrejectedtriplets.curated_dataset.jsonl, generating 29 high-quality preference pairs with a validated schema formlx-lm.training/DPO_REPORT.mdwith validation metrics and alignment analysis.Why This Matters
This provides the machinery for Timmy to learn from his own best vs. worst behaviors, reinforcing brevity, honesty, and sovereign tone through a verifiable, local pipeline.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
Hey Timmy this is my fault, I didn't tell manus about the rule. Please review this without the net 10 rule and we will come up with a place ot cut later.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
❌ Net +82 lines exceeds the 10-line limit. Find 72 lines to cut. See CONTRIBUTING.md.
Pull request closed