Downloads · 30 days
8
47% of all-time downloads
tinyllama-mentalchat16k
advy/tinyllama-mentalchat16k
tinyllama-mentalchat16k is a machine learning model from advy. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
17
Public
Repo size
1.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt101 MB · 48%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025
- SHA
- 81ca6a46
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. -->
tinyllama-mentalchat16k
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7700
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9602 | 0.1496 | 100 | 0.9461 |
| 0.9058 | 0.2992 | 200 | 0.8929 |
| 0.8474 | 0.4488 | 300 | 0.8695 |
| 0.8474 | 0.5984 | 400 | 0.8520 |
| 0.8393 | 0.7479 | 500 | 0.8393 |
| 0.8246 | 0.8975 | 600 | 0.8247 |
| 0.7652 | 1.0471 | 700 | 0.8210 |
| 0.7436 | 1.1967 | 800 | 0.8142 |
| 0.7248 | 1.3463 | 900 | 0.8076 |
| 0.7341 | 1.4959 | 1000 | 0.8008 |
| 0.7295 | 1.6455 | 1100 | 0.7940 |
| 0.7073 | 1.7951 | 1200 | 0.7896 |
| 0.7209 | 1.9447 | 1300 | 0.7836 |
| 0.6142 | 2.0942 | 1400 | 0.7935 |
| 0.6168 | 2.2438 | 1500 | 0.7946 |
| 0.6068 | 2.3934 | 1600 | 0.7908 |
| 0.6264 | 2.5430 | 1700 | 0.7899 |
| 0.6187 | 2.6926 | 1800 | 0.7833 |
| 0.6049 | 2.8422 | 1900 | 0.7842 |
| 0.6007 | 2.9918 | 2000 | 0.7816 |
| 0.5308 | 3.1414 | 2100 | 0.8032 |
| 0.5341 | 3.2909 | 2200 | 0.8018 |
| 0.5376 | 3.4405 | 2300 | 0.8013 |
| 0.5365 | 3.5901 | 2400 | 0.8018 |
| 0.5358 | 3.7397 | 2500 | 0.8010 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.4.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3
- Library
- peft
- License
- apache-2.0
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025