Hugging Face's logo

andretisch
/
Qwen2.5_1.5B_Ru_V0.1.2

Text Generation
Safetensors
Russian
English
Chinese
qwen2
conversational
Model card Files
xet
 Community
1

Обучена на P40 в течении месяца в 23 этапа. Исходный train_loss: 1.234700, конечный train_loss: 0.401200.

Downloads last month
2
Safetensors
Model size
2B params
Tensor type
F16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for andretisch/Qwen2.5_1.5B_Ru_V0.1.2

Base model

Qwen/Qwen2.5-1.5B
Finetuned
Qwen/Qwen2.5-1.5B-Instruct
Finetuned
(1537)
this model
Quantizations
1 model

Dataset used to train andretisch/Qwen2.5_1.5B_Ru_V0.1.2