Update README.md
Browse files
README.md
CHANGED
@@ -8,14 +8,27 @@ tags:
|
|
8 |
- mistral
|
9 |
- gguf
|
10 |
base_model: gordicaleksa/YugoGPT
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
-
# Quantized
|
14 |
|
15 |
- **Quantized by:** datatab
|
16 |
- **License:** apache-2.0
|
17 |
- **Author of model :** gordicaleksa/YugoGPT
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
# Quant. preference
|
21 |
|
|
|
8 |
- mistral
|
9 |
- gguf
|
10 |
base_model: gordicaleksa/YugoGPT
|
11 |
+
model_creator: Gordic Aleksa
|
12 |
+
model_type: mistral
|
13 |
+
quantized_by: datatab
|
14 |
---
|
15 |
|
16 |
+
# YugoGPT-Quantized-GGUF
|
17 |
|
18 |
- **Quantized by:** datatab
|
19 |
- **License:** apache-2.0
|
20 |
- **Author of model :** gordicaleksa/YugoGPT
|
21 |
|
22 |
+
<!-- description start -->
|
23 |
+
## Description
|
24 |
+
|
25 |
+
This repo contains YugoGPT - the best open-source base 7B LLM for BCS (Bosnian, Croatian, Serbian) languages developed by Aleksa Gordić.
|
26 |
+
|
27 |
+
Eval was computed using https://github.com/gordicaleksa/serbian-llm-eval
|
28 |
+
|
29 |
+
It was trained on tens of billions of BCS tokens and is based off of [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-v0.1).
|
30 |
+
|
31 |
+
<!-- description end -->
|
32 |
|
33 |
# Quant. preference
|
34 |
|