CompassioninMachineLearning
/

qwen-compassion-midtrain-seed2-CPT-best

Model card Files Files and versions

qwen-compassion-midtrain-seed2-CPT-best

Merged bf16 model from CompassioninMachineLearning/Qwen3-8b-compassion-seed2-20261001-CPT-LoRA-checkpoints checkpoint-750: the run's lowest validation loss (1.5580 at step 750; the run continued to step 1000). Built by pilot/erosion/merge_best_cpt.py.

Downloads last month: 134

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-compassion-midtrain-seed2-CPT-best

Base model

Qwen/Qwen3-8B-Base

Finetuned

(628)

this model

Finetunes