Views
No views yet
| 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 | (not set) |
| Training script | scripts/grpo_4h100_qwen_lengthpenalty_train.sh |
mainmain-step-<N>1from transformers import AutoModelForCausalLM
2
3model = AutoModelForCausalLM.from_pretrained(
4 "agurung/flawed-fictions-qwen3-4b-lengthpenalty",
5 revision="main",
6 device_map="auto",
7 torch_dtype="auto",
8)