A newer version of this model is available: kxdw2580/DeepSeek-R1-0528-Qwen3-8B-catgirl-v2.5

We have released the updated v2-qwen dataset , designed to evaluate performance advantages of large-scale models.

To address limitations in previous model iterations, we implemented a hybrid fine-tuning approach combining v2-common with other v2-qwen subsets. This significantly reduced redundant reasoning processes and hallucinations in routine responses, while improvements were also observed in non-reasoning modes .

Additionally, during fine-tuning, LoRA + bitsandbytes 8-bit quantization was employed to accelerate training. The model's efficiency may be compromised compared to fully-precision models.

Downloads last month
46
Safetensors
Model size
8.19B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kxdw2580/DeepSeek-R1-0528-Qwen3-8B-Catgirl-0531-test-mix

Finetuned
(22)
this model

Dataset used to train kxdw2580/DeepSeek-R1-0528-Qwen3-8B-Catgirl-0531-test-mix