Downloads · 30 days
13
1% of all-time downloads
llama-384-4L
stage-babylm/llama-384-4L
llama-384-4L is a text generation model from stage-babylm. Use it when you need the model to write or continue text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
1.8K
Public
Parameters
7.9M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors31.4 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Aug 11, 2026
- Updated
- Aug 17, 2026
- SHA
- 7db7c385
Try a prompt
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-384-4L
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7420
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: 0.0018
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0 | 0 | 6.9477 |
| 2.4026 | 0.0500 | 2014 | 2.4169 |
| 2.1915 | 0.1000 | 4028 | 2.2010 |
| 2.1044 | 0.1500 | 6042 | 2.1186 |
| 2.0562 | 0.2000 | 8056 | 2.0769 |
| 2.0325 | 0.2500 | 10070 | 2.0491 |
| 2.0060 | 0.3000 | 12084 | 2.0198 |
| 1.9784 | 0.3500 | 14098 | 2.0017 |
| 1.9561 | 0.4000 | 16112 | 1.9806 |
| 1.9473 | 0.4500 | 18126 | 1.9573 |
| 1.9130 | 0.5000 | 20140 | 1.9361 |
| 1.8968 | 0.5500 | 22154 | 1.9130 |
| 1.8590 | 0.6000 | 24168 | 1.8885 |
| 1.8464 | 0.6500 | 26182 | 1.8632 |
| 1.8214 | 0.7000 | 28196 | 1.8374 |
| 1.7862 | 0.7500 | 30210 | 1.8096 |
| 1.7621 | 0.8000 | 32224 | 1.7872 |
| 1.7466 | 0.8500 | 34238 | 1.7656 |
| 1.7271 | 0.9000 | 36252 | 1.7510 |
| 1.7184 | 0.9500 | 38266 | 1.7437 |
| 1.7134 | 1.0 | 40278 | 1.7420 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.13.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Aug 11, 2026
- Updated
- Aug 17, 2026