snowman0919
/

qwen38-executor-27b-checkpoints-v2

Model card Files Files and versions

Qwen3.8-27B Executor v2

QLoRA adapter trained from the unmodified base model. Load this repository as a PEFT adapter over Qwen/Qwen3.8-27B.

Base revision: 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
Dataset revision: c4c267e27ca3cba0736f24d2c2d3997f8b12653e
Native maximum context: 262,144 tokens
Long rows: preserved whole up to 262,144; longer rows use 8,192-token overlap windows
Quantized training: 4-bit NF4 with double quantization and BF16 compute
LoRA: r=32, alpha=64, dropout=0.0
Text: 2180 steps, 17440 deterministic rows, at least 40% Korean
Vision: 1275 steps over every validated vision row
Checkpoints: snowman0919/qwen38-executor-27b-checkpoints-v2 every 5 steps
Evaluation: HLE closed/web, TerminalBench 2.1, and OSWorld are run after training; OSWorld is not independent because related trajectories are intentionally included.

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for snowman0919/qwen38-executor-27b-checkpoints-v2

Base model

Qwen/Qwen3.8-27B

Adapter

(44)

this model

Dataset used to train snowman0919/qwen38-executor-27b-checkpoints-v2