Using opencsg/csg-wukong-2b-chinese-fineweb-edu as base model, we fine-tune it on smoltalk-chinese for 2 epoch
learning rate = 3e-4 ; global batch size = 32 ; lr scheduler=cosine

Safetensors

Model size

2.17B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for opencsg/csg-wukong-2b-smoltalk-chinese

Base model

Finetuned

(1)

this model

Finetunes

Dataset used to train opencsg/csg-wukong-2b-smoltalk-chinese