Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,17 @@ base_model:
|
|
| 8 |
- google/gemma-3-1b-it-qat-q4_0-unquantized
|
| 9 |
tags:
|
| 10 |
- meme
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
- google/gemma-3-1b-it-qat-q4_0-unquantized
|
| 9 |
tags:
|
| 10 |
- meme
|
| 11 |
+
- crysis
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [google/gemma-3-1b-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-3-1b-it-qat-q4_0-unquantized) on [AnonSOB/Crysis](https://huggingface.co/datasets/AnonSOB/Crysis).
|
| 15 |
+
|
| 16 |
+
The following hyperparameters were used during training:
|
| 17 |
+
- learning_rate: 1e-5
|
| 18 |
+
- train_batch_size: 5
|
| 19 |
+
- seed: 0
|
| 20 |
+
- num_epochs: 6000
|
| 21 |
+
|
| 22 |
+
Trained with mlx-lm.
|
| 23 |
+
Thank you Alex Ziskind for original TinyLlama Crysis ❤️
|
| 24 |
+
This model is unquantized. I dont know why I trained it on Gemma 3 QAT because it acts weird when quantized.
|