Downloads · 30 days
5
16% of all-time downloads
qwen3-8b-belebele-lora-npi-deva
xummer/qwen3-8b-belebele-lora-npi-deva
qwen3-8b-belebele-lora-npi-deva is a text generation model from xummer. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
31
Public
Repo size
885 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 94%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- other
- Access
- Public
- Created
- Mar 6, 2026
- Updated
- Mar 6, 2026
- SHA
- 5d3002ca
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
belebele_npi_Deva
This model is a fine-tuned version of Qwen/Qwen3-8B on the belebele_npi_Deva_train dataset. It achieves the following results on the evaluation set:
- Loss: 0.0800
- Accuracy: 0.9817
- Mcq Accuracy: 0.8333
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mcq Accuracy |
|---|---|---|---|---|---|
| 0.0688 | 1.1765 | 40 | 0.0814 | 0.9768 | 0.7692 |
| 0.0355 | 2.3529 | 80 | 0.0724 | 0.9820 | 0.8333 |
| 0.0227 | 3.5294 | 120 | 0.0766 | 0.9809 | 0.7949 |
| 0.0173 | 4.7059 | 160 | 0.0799 | 0.9811 | 0.8077 |
Framework versions
- PEFT 0.18.1
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Text Generation
- Library
- peft
- License
- other
- Created
- Mar 6, 2026
- Updated
- Mar 6, 2026