Quan
Collection
Qwen with Vietnamese continue pretrained and SFT
•
4 items
•
Updated
Qwen-1.8B finetuned on bilingual English-Vietnamese Data.
ChatML, same as VinaLlama
<|im_start|>system
Bạn là một trợ lí AI hữu ích. Hãy trả lời người dùng một cách chính xác.
<|im_end|>
<|im_start|>user
Hello world!<|im_end|>
<|im_start|>assistant
This model is a fine-tuned version of KnutJaegersberg/Qwen-1_8B-Llamafied on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.8123 | 1.02 | 2356 | 0.8183 |
0.7358 | 2.02 | 4713 | 0.7790 |
0.6379 | 3.02 | 7071 | 0.7822 |
0.5762 | 3.94 | 9252 | 0.8096 |
Base model
KnutJaegersberg/Qwen-1_8B-Llamafied