Update README.md
Browse files
README.md
CHANGED
@@ -10,10 +10,22 @@ tags:
|
|
10 |
|
11 |
# Chikuma
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
* [sethuiyer/SynthIQ-7b](https://huggingface.co/sethuiyer/SynthIQ-7b)
|
15 |
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
|
16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
## 🧩 Configuration
|
18 |
|
19 |
```yaml
|
|
|
10 |
|
11 |
# Chikuma
|
12 |
|
13 |
+
<p align="center">
|
14 |
+
<img src="https://huggingface.co/sethuiyer/Chikuma/resolve/main/chikuma.webp" height="256px" alt="Chikuma">
|
15 |
+
</p>
|
16 |
+
|
17 |
+
# Chikuma
|
18 |
+
|
19 |
+
Chikuma is a 10.7B parameter model and is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
20 |
* [sethuiyer/SynthIQ-7b](https://huggingface.co/sethuiyer/SynthIQ-7b)
|
21 |
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
|
22 |
|
23 |
+
The name "Chikuma" is inspired by the [Chikuma River](https://en.wikipedia.org/wiki/Shinano_River), the longest in Japan, known for its continuous flow and meandering path.
|
24 |
+
This metaphorically represents the model's depth, fluidity, and adaptability in processing and understanding language.
|
25 |
+
|
26 |
+
It also perfectly fits the approach taken here - Depth Upscaling, inspired by SOLAR 10.7B.
|
27 |
+
|
28 |
+
|
29 |
## 🧩 Configuration
|
30 |
|
31 |
```yaml
|