Downloads · 30 days
12
7% of all-time downloads
Llama-3.2-1B-Instruct-tuned
PracticalWork/Llama-3.2-1B-Instruct-tuned
Llama-3.2-1B-Instruct-tuned is a text generation model from PracticalWork. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama3.2.
should probably proofread and complete it, then remove this comment. --
All-time downloads
180
Public
Repo size
17.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json17.3 MB · 99%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Jul 30, 2025
- Updated
- Sep 19, 2025
- SHA
- c3cfcc5f
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. -->
Llama-3.2-1B-Instruct-tuned
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5964
- Perplexity: 4.9351
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.003
- train_batch_size: 12
- eval_batch_size: 12
- 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: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|---|---|---|---|---|
| No log | 0 | 0 | 4.5699 | 96.5354 |
| No log | 0.6011 | 333 | 1.7253 | 5.6141 |
| 1.8003 | 1.2022 | 666 | 1.6644 | 5.2825 |
| 1.8003 | 1.8032 | 999 | 1.6342 | 5.1252 |
| 1.6299 | 2.4043 | 1332 | 1.6094 | 5.0000 |
| 1.6299 | 3 | 1664 | 1.5964 | 4.9351 |
Framework versions
- PEFT 0.16.0
- Transformers 4.54.1
- Pytorch 2.7.1+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4
- Task
- Text Generation
- Library
- peft
- License
- llama3.2
- Created
- Jul 30, 2025
- Updated
- Sep 19, 2025