shinich001
/

qwen3-4b-h100-v5-hard-ep2

Text Generation

structured-output

Model card Files Files and versions

qwen3-4b-h100-v5-hard-ep2

This LoRA adapter is highly optimized for complex structured outputs (JSON/XML/YAML/CSV/TOML). Trained on H100 with a blend of two datasets (10k rows total) and heavily preprocessed to remove CoT traces and markdown artifacts.

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Max sequence length: 2560
Epochs: 2
Learning rate: 2e-5
Effective Batch size: 32 (BS=16, GradAccum=2)
Strategy: Phase 1 & Phase 2 mixed, custom output stripping applied.

Downloads last month: 4

Model tree for shinich001/qwen3-4b-h100-v5-hard-ep2

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5555)

this model

Dataset used to train shinich001/qwen3-4b-h100-v5-hard-ep2