CompassioninMachineLearning
/

qwen-urban-midtrain-seed1-CPT-best

Model card Files Files and versions

qwen-urban-midtrain-seed1-CPT-best

Merged bf16 model from BrandonHowe/Qwen3-8b-urban-qwen-seed1-20260930-CPT-LoRA-checkpoints checkpoint-750: the run's lowest validation loss (1.5735 at step 750; the run continued to step 1500). Built by pilot/erosion/merge_best_cpt.py.

Downloads last month: 40

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

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

Model tree for CompassioninMachineLearning/qwen-urban-midtrain-seed1-CPT-best

Base model

Qwen/Qwen3-8B-Base

Finetuned

(651)

this model