agurung/flawed-fictions-qwen3-4b-lengthpenalty-litereason

Flawed Fictions GRPO (qwen3_4b_lengthpenalty_litereason)

Training Details

Base model	Qwen/Qwen3-4B-Instruct-2507
Task	Continuity error detection (\boxed{Yes} / \boxed{No})
W&B project	flawed_fictions_rl
W&B group	(not set)
W&B runs	q3dxq5tg
Training script	scripts/grpo_4h100_smallqwen_lengthpenalty_litereason_train.sh

Checkpoint Revisions

• Branch head (latest): main
• Per-checkpoint tags: main-step-<N>

Usage

from litereason.causal_lm_with_reasoning import AutoModelForCausalLMWithReasoning

model = AutoModelForCausalLMWithReasoning.from_pretrained(
    "agurung/flawed-fictions-qwen3-4b-lengthpenalty-litereason",
    revision="main",
    device_map="auto",
    torch_dtype="auto",
)