aashish1904
commited on
Commit
•
3844bd7
1
Parent(s):
23fc600
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
|
4 |
+
base_model:
|
5 |
+
- bunnycore/LLama-3.1-Hyper-Stock
|
6 |
+
- bunnycore/LLama-3.1-8B-HyperNova-abliteration
|
7 |
+
- bunnycore/LLama-3.1-8b-Ultra-Max-Pro
|
8 |
+
- bunnycore/Llama-3.1-8B-OmniMatrix
|
9 |
+
- leafspark/Llama-3.1-8B-MultiReflection-Instruct
|
10 |
+
library_name: transformers
|
11 |
+
tags:
|
12 |
+
- mergekit
|
13 |
+
- merge
|
14 |
+
|
15 |
+
|
16 |
+
---
|
17 |
+
|
18 |
+
[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
|
19 |
+
|
20 |
+
|
21 |
+
# QuantFactory/LLama-3.1-8B-Matrix-GGUF
|
22 |
+
This is quantized version of [bunnycore/LLama-3.1-8B-Matrix](https://huggingface.co/bunnycore/LLama-3.1-8B-Matrix) created using llama.cpp
|
23 |
+
|
24 |
+
# Original Model Card
|
25 |
+
|
26 |
+
# merge
|
27 |
+
|
28 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
29 |
+
|
30 |
+
## Merge Details
|
31 |
+
### Merge Method
|
32 |
+
|
33 |
+
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [bunnycore/LLama-3.1-Hyper-Stock](https://huggingface.co/bunnycore/LLama-3.1-Hyper-Stock) as a base.
|
34 |
+
|
35 |
+
### Models Merged
|
36 |
+
|
37 |
+
The following models were included in the merge:
|
38 |
+
* [bunnycore/LLama-3.1-8B-HyperNova-abliteration](https://huggingface.co/bunnycore/LLama-3.1-8B-HyperNova-abliteration)
|
39 |
+
* [bunnycore/LLama-3.1-8b-Ultra-Max-Pro](https://huggingface.co/bunnycore/LLama-3.1-8b-Ultra-Max-Pro)
|
40 |
+
* [bunnycore/Llama-3.1-8B-OmniMatrix](https://huggingface.co/bunnycore/Llama-3.1-8B-OmniMatrix)
|
41 |
+
* [leafspark/Llama-3.1-8B-MultiReflection-Instruct](https://huggingface.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct)
|
42 |
+
|
43 |
+
### Configuration
|
44 |
+
|
45 |
+
The following YAML configuration was used to produce this model:
|
46 |
+
|
47 |
+
```yaml
|
48 |
+
models:
|
49 |
+
- model: leafspark/Llama-3.1-8B-MultiReflection-Instruct
|
50 |
+
- model: bunnycore/Llama-3.1-8B-OmniMatrix
|
51 |
+
- model: bunnycore/LLama-3.1-8B-HyperNova-abliteration
|
52 |
+
- model: bunnycore/LLama-3.1-8b-Ultra-Max-Pro
|
53 |
+
merge_method: model_stock
|
54 |
+
base_model: bunnycore/LLama-3.1-Hyper-Stock
|
55 |
+
dtype: bfloat16
|
56 |
+
|
57 |
+
```
|
58 |
+
|