Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- miqu
|
7 |
+
- 70b model
|
8 |
+
- cat
|
9 |
+
- miqu cat
|
10 |
+
---
|
11 |
+
## Welcome to Miqu Cat: A 70B Miqu Lora Fine-Tune
|
12 |
+
|
13 |
+
Introducing **Miqu Cat**, an advanced model fine-tuned by Dr. Kal'tsit then quanted for the the ExllamaV2 project, bringing the model down to an impressive 4.8 bits per weight (bpw). This fine-tuning allows those with limited computational resources to explore its capabilities without compromise.
|
14 |
+
|
15 |
+
### Competitive Edge - *meow!*
|
16 |
+
|
17 |
+
Miqu Cat stands out in the arena of Miqu fine-tunes, consistently performing admirably in tests and comparisons. It’s crafted to be less restrictive and more robust than its predecessors and variants, making it a versatile tool in AI-driven applications.
|
18 |
+
|
19 |
+
### How to Use Miqu Cat: The Nitty-Gritty
|
20 |
+
|
21 |
+
Miqu Cat operates on the **CHATML** prompt format, designed for straightforward and effective interaction. Whether you're integrating it into existing systems or using it for new projects, its flexible prompt structure facilitates ease of use.
|
22 |
+
|
23 |
+
### Training Specs
|
24 |
+
|
25 |
+
- **Dataset**: 1.5 GB
|
26 |
+
- **Compute**: Dual setup of 8xA100 nodes
|
27 |
+
- **Duration**: Approximately 1000 hours of intensive training
|
28 |
+
|
29 |
+
### Meet the Author
|
30 |
+
|
31 |
+
**Dr. Kal'tsit** has been at the forefront of this fine-tuning process, ensuring that Miqu Cat gives the user a unique feel.
|