Update README.md
Browse files
README.md
CHANGED
|
@@ -8,20 +8,40 @@ tags:
|
|
| 8 |
- merge
|
| 9 |
|
| 10 |
---
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
| 21 |
|
| 22 |
This model was merged using a multi-step merge method.
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
The following models were included in the merge:
|
| 27 |
* [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B)
|
|
@@ -31,7 +51,7 @@ The following models were included in the merge:
|
|
| 31 |
* [tokyotech-llm/Llama-3-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1)
|
| 32 |
* [Nitral-AI/Hathor_Respawn-L3-8B-v0.8](https://huggingface.co/Nitral-AI/Hathor_Respawn-L3-8B-v0.8)
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
The following YAML configuration was used to produce this model:
|
| 37 |
|
|
@@ -74,4 +94,7 @@ models:
|
|
| 74 |
weight: 0.15
|
| 75 |
merge_method: linear
|
| 76 |
dtype: float32
|
| 77 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
- merge
|
| 9 |
|
| 10 |
---
|
| 11 |
+
<!DOCTYPE html>
|
| 12 |
+
<style>
|
| 13 |
+
|
| 14 |
+
h1 {
|
| 15 |
+
color: #FF0000; /* Red color */
|
| 16 |
+
font-size: 1.25em; /* Larger font size */
|
| 17 |
+
text-align: left; /* Center alignment */
|
| 18 |
+
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5); /* Shadow effect */
|
| 19 |
+
background: linear-gradient(90deg, #FF0000, #FF7F50); /* Gradient background */
|
| 20 |
+
-webkit-background-clip: text; /* Clipping the background to text */
|
| 21 |
+
-webkit-text-fill-color: transparent; /* Making the text transparent */
|
| 22 |
+
}
|
| 23 |
+
</style>
|
| 24 |
+
<html lang="en">
|
| 25 |
+
<head>
|
| 26 |
+
</head>
|
| 27 |
+
<body>
|
| 28 |
+
<h1>SwallowMaid-8B-Llama-3-SPPO-abliterated</h1>
|
| 29 |
|
| 30 |
|
| 31 |
|
| 32 |
+
<h1>Quants</h1>
|
| 33 |
+
* [GGUF Q8_0](https://huggingface.co/v000000/SwallowMaid-8B-L3-SPPO-abliterated-Q8_0-GGUF)
|
| 34 |
+
|
| 35 |
+
<h1>merge</h1>
|
| 36 |
|
| 37 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 38 |
|
| 39 |
+
<h1>Merge Details</h1>
|
| 40 |
+
<h1>Merge Method</h1>
|
| 41 |
|
| 42 |
This model was merged using a multi-step merge method.
|
| 43 |
|
| 44 |
+
<h1>Models Merged</h1>
|
| 45 |
|
| 46 |
The following models were included in the merge:
|
| 47 |
* [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B)
|
|
|
|
| 51 |
* [tokyotech-llm/Llama-3-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1)
|
| 52 |
* [Nitral-AI/Hathor_Respawn-L3-8B-v0.8](https://huggingface.co/Nitral-AI/Hathor_Respawn-L3-8B-v0.8)
|
| 53 |
|
| 54 |
+
<h1>Configuration</h1>
|
| 55 |
|
| 56 |
The following YAML configuration was used to produce this model:
|
| 57 |
|
|
|
|
| 94 |
weight: 0.15
|
| 95 |
merge_method: linear
|
| 96 |
dtype: float32
|
| 97 |
+
```
|
| 98 |
+
|
| 99 |
+
</body>
|
| 100 |
+
</html>
|