Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
base_model:
|
| 5 |
+
- huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
|
| 6 |
+
- IlyaGusev/saiga_llama3_8b
|
| 7 |
+
- lightblue/suzume-llama-3-8B-multilingual
|
| 8 |
+
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full
|
| 9 |
+
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half
|
| 10 |
+
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25
|
| 11 |
+
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75
|
| 12 |
+
library_name: transformers
|
| 13 |
+
tags:
|
| 14 |
+
- mergekit
|
| 15 |
+
- merge
|
| 16 |
+
- bfloat16
|
| 17 |
+
- safetensors
|
| 18 |
+
- 8b
|
| 19 |
+
- chat
|
| 20 |
+
- conversational
|
| 21 |
+
language:
|
| 22 |
+
- de
|
| 23 |
+
- en
|
| 24 |
+
- es
|
| 25 |
+
- fr
|
| 26 |
+
- hi
|
| 27 |
+
- it
|
| 28 |
+
- ja
|
| 29 |
+
- pt
|
| 30 |
+
- ru
|
| 31 |
+
- th
|
| 32 |
+
- zh
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
[](https://hf.co/QuantFactory)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
# QuantFactory/Multilingual-SaigaSuzume-8B-GGUF
|
| 41 |
+
This is quantized version of [Khetterman/Multilingual-SaigaSuzume-8B](https://huggingface.co/Khetterman/Multilingual-SaigaSuzume-8B) created using llama.cpp
|
| 42 |
+
|
| 43 |
+
# Original Model Card
|
| 44 |
+
|
| 45 |
+
# Multilingual-SaigaSuzume-8B
|
| 46 |
+
|
| 47 |
+
>Your words are like rain falling from heaven on a tower in a sinful land; can anyone in Babylon understand them?
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
This model was created as the basis of multilingual abilities for other models. I think it will be very useful as an integral part of your model. There is some censorship, keep this in mind.
|
| 52 |
+
|
| 53 |
+
## Merge Details
|
| 54 |
+
### Method
|
| 55 |
+
|
| 56 |
+
This is a simple, but usefull merge of **7 cool models**, created using [mergekit](https://github.com/arcee-ai/mergekit).
|
| 57 |
+
|
| 58 |
+
### Models
|
| 59 |
+
|
| 60 |
+
The following models were included in the merge:
|
| 61 |
+
|
| 62 |
+
* [huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated)
|
| 63 |
+
* [IlyaGusev/saiga_llama3_8b](https://huggingface.co/IlyaGusev/saiga_llama3_8b)
|
| 64 |
+
* [lightblue/suzume-llama-3-8B-multilingual](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual)
|
| 65 |
+
* [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full)
|
| 66 |
+
* [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half)
|
| 67 |
+
* [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25)
|
| 68 |
+
* [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75)
|
| 69 |
+
|
| 70 |
+
### Configuration
|
| 71 |
+
|
| 72 |
+
The following YAML configurations was used to produce this model:
|
| 73 |
+
|
| 74 |
+
```yaml
|
| 75 |
+
# Multilingual-SaigaSuzume-8B-BFH
|
| 76 |
+
models:
|
| 77 |
+
- model: lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full
|
| 78 |
+
- model: IlyaGusev/saiga_llama3_8b
|
| 79 |
+
- model: lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half
|
| 80 |
+
merge_method: model_stock
|
| 81 |
+
base_model: huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
|
| 82 |
+
dtype: bfloat16
|
| 83 |
+
|
| 84 |
+
# Multilingual-SaigaSuzume-8B-BTP
|
| 85 |
+
models:
|
| 86 |
+
- model: lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75
|
| 87 |
+
- model: IlyaGusev/saiga_llama3_8b
|
| 88 |
+
- model: lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25
|
| 89 |
+
merge_method: model_stock
|
| 90 |
+
base_model: huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
|
| 91 |
+
dtype: bfloat16
|
| 92 |
+
|
| 93 |
+
# Multilingual-SaigaSuzume-8B-Classic
|
| 94 |
+
models:
|
| 95 |
+
- model: IlyaGusev/saiga_llama3_8b
|
| 96 |
+
- model: lightblue/suzume-llama-3-8B-multilingual
|
| 97 |
+
merge_method: model_stock
|
| 98 |
+
base_model: huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
|
| 99 |
+
dtype: bfloat16
|
| 100 |
+
|
| 101 |
+
# Multilingual-SaigaSuzume-8B
|
| 102 |
+
models:
|
| 103 |
+
- model: Multilingual-SaigaSuzume-8B-BFH
|
| 104 |
+
- model: Multilingual-SaigaSuzume-8B-BTP
|
| 105 |
+
merge_method: model_stock
|
| 106 |
+
base_model: Multilingual-SaigaSuzume-8B-Classic
|
| 107 |
+
dtype: bfloat16
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
+
>My thanks to the authors of the original models, your work is incredible. Have a good time 🖤
|
| 111 |
+
|