Modelpublic

g30rv17ys/clawpathy-4b-scriptwriting-reasoning

sourceHugging Faceupdated 7mo agoView on Hugging Face

0likes

Model Card

clawpathy-4b-scriptwriting-reasoning

Trained with Clawpathy using the Tinker platform.

Parameter	Value
Base model	Qwen/Qwen3-8B
Method	Supervised Fine-Tuning
Dataset	MuratcanKoylan/impossible-moments
LoRA rank	32
Learning rate	0.00024000000000000003
Steps	200
Final loss	0.617072
Tinker sampler path	`tinker://a7af9bb1-e08e-53b0-b645-6db86439b1b1:train:0/sampler_weights/clawpathy-2797142f-590-final`
Tinker state path	`tinker://a7af9bb1-e08e-53b0-b645-6db86439b1b1:train:0/weights/clawpathy-2797142f-590-state`

No evaluation results available.