Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# godot_dodo_4x_60k_starcoder_15b_2ep_ggml_q4_1
|
2 |
+
|
3 |
+
## Model details
|
4 |
+
|
5 |
+
This is a 4-bit quantized ggml conversion of [minosu/godot_dodo_4x_60k_starcoder_15b_2ep](https://huggingface.co/minosu/godot_dodo_4x_60k_starcoder_15b_2ep) for use with [ggml](https://github.com/ggerganov/ggml).
|
6 |
+
|
7 |
+
Trained in May 2023.
|
8 |
+
|
9 |
+
Godot-Dodo models are instruction-following models finetuned from open-source base models.
|
10 |
+
|
11 |
+
Please refer to the README of the [GitHub repository](https://github.com/minosvasilias/godot-dodo) for detailed information.
|
12 |
+
|
13 |
+
### Evaluation datasets
|
14 |
+
|
15 |
+
The model was evaluated using code instruction prompts. More details in the [GitHub repository](https://github.com/minosvasilias/godot-dodo).
|
16 |
+
|
17 |
+
### Training dataset
|
18 |
+
|
19 |
+
The model was trained on a 60k rows instruction following dataset, which is released in the [Github repository](https://github.com/minosvasilias/godot-dodo).
|
20 |
+
|
21 |
+
### Training parameters
|
22 |
+
|
23 |
+
For exact parameters used, please refer to [this page](https://github.com/minosvasilias/godot-dodo/tree/main/models/godot_dodo_4x_60k_starcoder_15b_2ep) in the GitHub repository.
|