Commit
•
b3b119f
1
Parent(s):
b95fcc1
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: llama2
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- not-for-all-audiences
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
# Venus 120b - version 1.2
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
## Overview
|
| 14 |
+
|
| 15 |
+
Version 1.2 of the Venus 120b lineup.
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
- A result of interleaving layers of [lizpreciatior/lzlv_70b_fp16_hf](https://huggingface.co/lizpreciatior/lzlv_70b_fp16_hf) with itself.
|
| 20 |
+
- The resulting model has 140 layers and approximately 122 billion parameters.
|
| 21 |
+
- See mergekit-config.yml for details on the merge method used.
|
| 22 |
+
- See the `exl2-*` branches for exllama2 quantizations. The 4.85 bpw quant should fit in 80GB VRAM, and the 3.0 bpw quant should (just barely) fit in 48GB VRAM with 4k context.
|
| 23 |
+
- Inspired by [Goliath-120b](https://huggingface.co/alpindale/goliath-120b)
|
| 24 |
+
|
| 25 |
+
**Warning: This model will produce NSFW content!**
|
| 26 |
+
|
| 27 |
+
## Results
|
| 28 |
+
|
| 29 |
+
Better at following instructions than both v1.1 and v1.0, and doesn't seem to suffer from censorship issues. Overall I like this version the most out of all the models I've created.
|