Downloads · 30 days
6
13% of all-time downloads
20numbeans-15000-Qwen_Qwen2.5-7B-Instruct_lora
dzhang019/20numbeans-15000-Qwen_Qwen2.5-7B-Instruct_lora
20numbeans-15000-Qwen_Qwen2.5-7B-Instruct_lora is a text generation model from dzhang019. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
45
Public
Repo size
1.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors162 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Dec 3, 2025
- Updated
- Dec 3, 2025
- SHA
- afa8fcd1
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. -->
20numbeans-15000-Qwen_Qwen2.5-7B-Instruct_lora
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6194
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5359 | 0.5236 | 100 | 0.5565 |
| 0.6126 | 1.0471 | 200 | 0.5504 |
| 0.509 | 1.5707 | 300 | 0.5592 |
| 0.431 | 2.0942 | 400 | 0.5757 |
| 0.4301 | 2.6178 | 500 | 0.5810 |
| 0.431 | 3.1414 | 600 | 0.6398 |
| 0.4047 | 3.6649 | 700 | 0.6208 |
| 0.3453 | 4.1885 | 800 | 0.7369 |
| 0.3393 | 4.7120 | 900 | 0.7307 |
| 0.1874 | 5.2356 | 1000 | 0.8825 |
| 0.2594 | 5.7592 | 1100 | 0.9202 |
| 0.1177 | 6.2827 | 1200 | 1.1571 |
| 0.1848 | 6.8063 | 1300 | 1.1725 |
| 0.1035 | 7.3298 | 1400 | 1.3685 |
| 0.0879 | 7.8534 | 1500 | 1.4279 |
| 0.0384 | 8.3770 | 1600 | 1.5605 |
| 0.0373 | 8.9005 | 1700 | 1.5722 |
| 0.0257 | 9.4241 | 1800 | 1.6143 |
| 0.0373 | 9.9476 | 1900 | 1.6194 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Dec 3, 2025
- Updated
- Dec 3, 2025