Flawed Fictions GRPO (qwen25_lengthpenalty)
Training Details
|
|
| Base model |
Qwen/Qwen2.5-7B-Instruct |
| Task |
Continuity error detection (\boxed{Yes} / \boxed{No}) |
| W&B group |
flawed_fictions_rl |
| W&B runs |
vttgr0i0 |
| Training script |
scripts/grpo_4h100_qwen_lengthpenalty_train.sh |
Checkpoint Revisions
- Branch head (latest):
main
- Per-checkpoint tags:
main-step-<N>
Usage
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"agurung/flawed-fictions-qwen25-7b-lengthpenalty",
revision="main",
device_map="auto",
torch_dtype="auto",
)
