Update README.md
Browse files
README.md
CHANGED
|
@@ -11,20 +11,61 @@ tags:
|
|
| 11 |
This model was converted to GGUF format from [`v000000/SwallowMaid-8B-L3-SPPO-abliterated`](https://huggingface.co/v000000/SwallowMaid-8B-L3-SPPO-abliterated) using llama.cpp
|
| 12 |
Refer to the [original model card](https://huggingface.co/v000000/SwallowMaid-8B-L3-SPPO-abliterated) for more details on the model.
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 21 |
|
| 22 |
-
|
| 23 |
-
|
| 24 |
|
| 25 |
This model was merged using a multi-step merge method.
|
| 26 |
|
| 27 |
-
|
| 28 |
|
| 29 |
The following models were included in the merge:
|
| 30 |
* [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B)
|
|
@@ -34,7 +75,7 @@ The following models were included in the merge:
|
|
| 34 |
* [tokyotech-llm/Llama-3-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1)
|
| 35 |
* [Nitral-AI/Hathor_Respawn-L3-8B-v0.8](https://huggingface.co/Nitral-AI/Hathor_Respawn-L3-8B-v0.8)
|
| 36 |
|
| 37 |
-
|
| 38 |
|
| 39 |
The following YAML configuration was used to produce this model:
|
| 40 |
|
|
@@ -77,4 +118,19 @@ models:
|
|
| 77 |
weight: 0.15
|
| 78 |
merge_method: linear
|
| 79 |
dtype: float32
|
| 80 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
This model was converted to GGUF format from [`v000000/SwallowMaid-8B-L3-SPPO-abliterated`](https://huggingface.co/v000000/SwallowMaid-8B-L3-SPPO-abliterated) using llama.cpp
|
| 12 |
Refer to the [original model card](https://huggingface.co/v000000/SwallowMaid-8B-L3-SPPO-abliterated) for more details on the model.
|
| 13 |
|
| 14 |
+
---
|
| 15 |
+
base_model:
|
| 16 |
+
- x0000001/mergekit-task_arithmetic-vlehhex
|
| 17 |
+
- grimjim/Llama-3-Instruct-abliteration-LoRA-8B
|
| 18 |
+
library_name: transformers
|
| 19 |
+
tags:
|
| 20 |
+
- mergekit
|
| 21 |
+
- merge
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
+
<!DOCTYPE html>
|
| 25 |
+
<style>
|
| 26 |
+
|
| 27 |
+
h1 {
|
| 28 |
+
color: #801ffa; /* Red color */
|
| 29 |
+
font-size: 1.25em; /* Larger font size */
|
| 30 |
+
text-align: left; /* Center alignment */
|
| 31 |
+
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5); /* Shadow effect */
|
| 32 |
+
background: linear-gradient(90deg, #801ffa, #e9a8fb); /* Gradient background */
|
| 33 |
+
-webkit-background-clip: text; /* Clipping the background to text */
|
| 34 |
+
-webkit-text-fill-color: transparent; /* Making the text transparent */
|
| 35 |
+
}
|
| 36 |
|
| 37 |
+
a {
|
| 38 |
+
color: #801ffa; /* Red color */
|
| 39 |
+
font-size: 1.25em; /* Larger font size */
|
| 40 |
+
text-align: left; /* Center alignment */
|
| 41 |
+
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5); /* Shadow effect */
|
| 42 |
+
background: linear-gradient(90deg, #801ffa, #e9a8fb); /* Gradient background */
|
| 43 |
+
-webkit-background-clip: text; /* Clipping the background to text */
|
| 44 |
+
-webkit-text-fill-color: transparent; /* Making the text transparent */
|
| 45 |
+
}
|
| 46 |
+
</style>
|
| 47 |
+
<html lang="en">
|
| 48 |
+
<head>
|
| 49 |
+
</head>
|
| 50 |
+
<body>
|
| 51 |
+
<h1>SwallowMaid-8B-Llama-3-SPPO-abliterated</h1>
|
| 52 |
+
Excellent "Llama-3-Instruct-8B-SPPO-Iter3" fully uncensored with 35% RP-Mix infused to gain roleplay capabilities and prose while attempting to preserve the qualities of Meta's Llama-3-Instruct finetune.
|
| 53 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
# <a>Quants</a>
|
| 57 |
+
* [GGUF Q8_0](https://huggingface.co/v000000/SwallowMaid-8B-L3-SPPO-abliterated-Q8_0-GGUF)
|
| 58 |
+
|
| 59 |
+
# <h1>merge</h1>
|
| 60 |
|
| 61 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 62 |
|
| 63 |
+
# <h1>Merge Details</h1>
|
| 64 |
+
# <h1>Merge Method</h1>
|
| 65 |
|
| 66 |
This model was merged using a multi-step merge method.
|
| 67 |
|
| 68 |
+
# <h1>Models Merged</h1>
|
| 69 |
|
| 70 |
The following models were included in the merge:
|
| 71 |
* [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B)
|
|
|
|
| 75 |
* [tokyotech-llm/Llama-3-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1)
|
| 76 |
* [Nitral-AI/Hathor_Respawn-L3-8B-v0.8](https://huggingface.co/Nitral-AI/Hathor_Respawn-L3-8B-v0.8)
|
| 77 |
|
| 78 |
+
# <h1>Configuration</h1>
|
| 79 |
|
| 80 |
The following YAML configuration was used to produce this model:
|
| 81 |
|
|
|
|
| 118 |
weight: 0.15
|
| 119 |
merge_method: linear
|
| 120 |
dtype: float32
|
| 121 |
+
```
|
| 122 |
+
|
| 123 |
+
# <h1>Prompt Template:</h1>
|
| 124 |
+
```bash
|
| 125 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
| 126 |
+
|
| 127 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
| 128 |
+
|
| 129 |
+
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
| 130 |
+
|
| 131 |
+
{output}<|eot_id|>
|
| 132 |
+
|
| 133 |
+
```
|
| 134 |
+
|
| 135 |
+
</body>
|
| 136 |
+
</html>
|