RedBlackBench Qwen3-14B SFT v2
Fine-tuned Qwen3-14B with improved hyperparameters.
Training Details
- Base: Qwen/Qwen3-14B
- LoRA: r=128, alpha=256 (improved from r=64)
- Data: 10,475 samples (deduplicated)
- LR: 5e-5 (optimized)
- Epochs: 3
- Hardware: NVIDIA H200
Improvements over v1
- LoRA rank increased: 64 → 128
- Learning rate optimized: 3e-5 → 5e-5
- Dataset cleaned: removed 6,146 duplicates
- Training data: 5,173 → 10,475 samples
Performance
- Overall reasoning: 90% (vs 80% base)
- Strategic reasoning: 100% (vs 75% base)
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B")
model = PeftModel.from_pretrained(base, "asukaredpanda/redblackbench-qwen3-14b-sft-v2")
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support