TheDrummer
commited on
Commit
•
9d72104
1
Parent(s):
6724427
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
---
|
4 |
+
|
5 |
+
# Join our Discord! https://discord.gg/Nbv9pQ88Xb
|
6 |
+
|
7 |
+
### Works on [Kobold 1.74](https://github.com/LostRuins/koboldcpp/releases/tag/v1.74)!
|
8 |
+
|
9 |
+
*([Layla (iOS / Android)](https://www.layla-network.ai/) support is in progress)*
|
10 |
+
|
11 |
+
---
|
12 |
+
|
13 |
+
[BeaverAI](https://huggingface.co/BeaverAI) proudly presents...
|
14 |
+
|
15 |
+
# Hubble 4B v1
|
16 |
+
|
17 |
+
*Equipped with his five senses, man explores the universe around him and calls the adventure 'Science'.*
|
18 |
+
|
19 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/R8_o3CCpTgKv5Wnnry7E_.png)
|
20 |
+
|
21 |
+
## Description
|
22 |
+
|
23 |
+
This is a finetune of Nvidia's Llama 3.1 4B Minitron - a shrunk down model of Llama 3.1 8B 128K.
|
24 |
+
|
25 |
+
### Usage
|
26 |
+
- ChatML or Text Completion
|
27 |
+
- Add `<|im_end|>` as a stop token
|
28 |
+
|
29 |
+
### Links
|
30 |
+
- Original: https://huggingface.co/TheDrummer/Hubble-4B-v1
|
31 |
+
- GGUF: https://huggingface.co/TheDrummer/Hubble-4B-v1-GGUF
|
32 |
+
|
33 |
+
### Technical Note
|
34 |
+
|
35 |
+
Hubble was trained on ChatML with `<|end_of_text|>` as the EOS token. If you encounter any issues with the model, please let me know!
|