blue-scrub-150M-it

Usage: (Reseacrh/ Non Commercial use)

LoRA instruction-tuning adapter trained for 3 epochs on 47,500 examples.

Base Model : mps/blue-scrub-150M

SFT data

Dataset Examples
MathInstruct 1,433
gsm8k 5,692
medmcqa 1,196
medqa-usmle-4-options 1,179
pubmedqa-grounded 466
sciq-grounded 4,284
synthetic-context-mismatch 2,375
synthetic-strict-format 9,500
tulu-evol-codealpaca 2,368
tulu-no-robots 4,754
tulu-oasst1 2,379
tulu-personahub-code 2,382
ultrachat_200k_sft 9,492
Total 47,500
Downloads last month
1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support