Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
thumbnail: null
|
| 5 |
+
tags:
|
| 6 |
+
- text generation
|
| 7 |
+
- instruct
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
inference: false
|
| 10 |
+
---
|
| 11 |
+
<h1 style="text-align: center">WizardLM 13b - Open Assistant</h1>
|
| 12 |
+
<h2 style="text-align: center">An instruction-following Llama model using full evolved-instructions. </h2>
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
This is a Lora merge of Open Assistant 13b - 4 Epoch with WizardLM-13b Uncensored. <br>
|
| 16 |
+
https://huggingface.co/serpdotai/llama-oasst-lora-13B <br>
|
| 17 |
+
https://huggingface.co/ehartford/WizardLM-13B-Uncensored
|
| 18 |
+
|
| 19 |
+
<html>
|
| 20 |
+
<head>
|
| 21 |
+
<style>
|
| 22 |
+
table {
|
| 23 |
+
border:1px solid #b3adad;
|
| 24 |
+
border-collapse:collapse;
|
| 25 |
+
padding:5px;
|
| 26 |
+
}
|
| 27 |
+
table th {
|
| 28 |
+
border:1px solid #b3adad;
|
| 29 |
+
padding:5px;
|
| 30 |
+
background: #f0f0f0;
|
| 31 |
+
color: #313030;
|
| 32 |
+
}
|
| 33 |
+
table td {
|
| 34 |
+
border:1px solid #b3adad;
|
| 35 |
+
text-align:center;
|
| 36 |
+
padding:5px;
|
| 37 |
+
background: #ffffff;
|
| 38 |
+
color: #313030;
|
| 39 |
+
}
|
| 40 |
+
</style>
|
| 41 |
+
</head>
|
| 42 |
+
<body>
|
| 43 |
+
<table>
|
| 44 |
+
<thead>
|
| 45 |
+
<tr>
|
| 46 |
+
<th>Model:</th>
|
| 47 |
+
<th>Wikitext2</th>
|
| 48 |
+
<th>Ptb-New</th>
|
| 49 |
+
<th>C4-New</th>
|
| 50 |
+
</tr>
|
| 51 |
+
</thead>
|
| 52 |
+
<tbody>
|
| 53 |
+
<tr>
|
| 54 |
+
<td></td>
|
| 55 |
+
<td></td>
|
| 56 |
+
<td></td>
|
| 57 |
+
<td></td>
|
| 58 |
+
</tr>
|
| 59 |
+
<tr>
|
| 60 |
+
<td></td>
|
| 61 |
+
<td></td>
|
| 62 |
+
<td></td>
|
| 63 |
+
<td></td>
|
| 64 |
+
</tr>
|
| 65 |
+
</tbody>
|
| 66 |
+
</table>
|
| 67 |
+
</body>
|
| 68 |
+
</html>
|
| 69 |
+
<br><b>Other benchmark scores at the bottom of readme.</b>
|
| 70 |
+
<hr>
|
| 71 |
+
Metharme 7B is an instruct model based on Meta's LLaMA-7B.
|
| 72 |
+
|
| 73 |
+
<hr>
|
| 74 |
+
<p><strong><font size="5">Click to Expand Benchmarks of different quantized variations</font></strong></p>
|
| 75 |
+
<strong><font size="4">The lower the number, the better the score.</font></strong>
|
| 76 |
+
<html>
|
| 77 |
+
<body>
|
| 78 |
+
<details>
|
| 79 |
+
<summary>Benchmarks Sorted by C4-New score</summary>
|
| 80 |
+
<table>
|
| 81 |
+
<thead>
|
| 82 |
+
<tr>
|
| 83 |
+
<th>GPTQ Variation:</th>
|
| 84 |
+
<th>Wikitext2</th>
|
| 85 |
+
<th>Ptb-New</th>
|
| 86 |
+
<th>C4-New</th>
|
| 87 |
+
</tr>
|
| 88 |
+
</thead>
|
| 89 |
+
<tbody>
|
| 90 |
+
<tr>
|
| 91 |
+
<td></td>
|
| 92 |
+
<td></td>
|
| 93 |
+
<td></td>
|
| 94 |
+
<td></td>
|
| 95 |
+
</tr>
|
| 96 |
+
<tr>
|
| 97 |
+
<td></td>
|
| 98 |
+
<td></td>
|
| 99 |
+
<td></td>
|
| 100 |
+
<td></td>
|
| 101 |
+
</tr>
|
| 102 |
+
<tr>
|