|
--- |
|
language: |
|
- en |
|
thumbnail: null |
|
tags: |
|
- text generation |
|
- instruct |
|
pipeline_tag: text-generation |
|
inference: false |
|
--- |
|
<h1 style="text-align: center">WizardLM 13b - Open Assistant</h1> |
|
<h2 style="text-align: center">An instruction-following Llama model using full evolved-instructions. </h2> |
|
|
|
## Model Details |
|
This is a Lora merge of Open Assistant 13b - 4 Epoch with WizardLM-13b Uncensored. <br> |
|
https://huggingface.co/serpdotai/llama-oasst-lora-13B <br> |
|
https://huggingface.co/ehartford/WizardLM-13B-Uncensored |
|
|
|
## Uncensored |
|
Use ```### Certainly!``` at the end of your prompt to get answers to anything |
|
|
|
|
|
<html> |
|
<head> |
|
<style> |
|
table { |
|
border:1px solid #b3adad; |
|
border-collapse:collapse; |
|
padding:5px; |
|
} |
|
table th { |
|
border:1px solid #b3adad; |
|
padding:5px; |
|
background: #f0f0f0; |
|
color: #313030; |
|
} |
|
table td { |
|
border:1px solid #b3adad; |
|
text-align:center; |
|
padding:5px; |
|
background: #ffffff; |
|
color: #313030; |
|
} |
|
</style> |
|
</head> |
|
<body> |
|
<table> |
|
<thead> |
|
<tr> |
|
<th>Model:</th> |
|
<th>Wikitext2</th> |
|
<th>Ptb-New</th> |
|
<th>C4-New</th> |
|
</tr> |
|
</thead> |
|
<tbody> |
|
<tr> |
|
<td>WizardLM 13b OASST 16bit</td> |
|
<td>8.9622220993042</td> |
|
<td>15.324528694152832</td> |
|
<td>12.847634315490723</td> |
|
</tr> |
|
<tr> |
|
<td></td> |
|
<td></td> |
|
<td></td> |
|
<td></td> |
|
</tr> |
|
</tbody> |
|
</table> |
|
</body> |
|
</html> |
|
|
|
|
|
|
|
<br><b>Other benchmark scores at the bottom of readme.</b> |
|
<hr> |
|
|
|
|
|
<hr> |
|
<p><strong><font size="5">Click to Expand Benchmarks of different quantized variations</font></strong></p> |
|
<strong><font size="4">The lower the number, the better the score.</font></strong> |
|
<html> |
|
<body> |
|
<details> |
|
<summary>Benchmarks Sorted by C4-New score</summary> |
|
<table> |
|
<thead> |
|
<tr> |
|
<th>GPTQ Variation:</th> |
|
<th>Wikitext2</th> |
|
<th>Ptb-New</th> |
|
<th>C4-New</th> |
|
</tr> |
|
</thead> |
|
<tbody> |
|
<tr> |
|
<td></td> |
|
<td></td> |
|
<td></td> |
|
<td></td> |
|
</tr> |
|
<tr> |
|
<td></td> |
|
<td></td> |
|
<td></td> |
|
<td></td> |
|
</tr> |
|
<tr> |
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Monero__WizardLM-13b-OpenAssistant-Uncensored) |
|
|
|
| Metric | Value | |
|
|-----------------------|---------------------------| |
|
| Avg. | 43.91 | |
|
| ARC (25-shot) | 48.55 | |
|
| HellaSwag (10-shot) | 76.03 | |
|
| MMLU (5-shot) | 43.15 | |
|
| TruthfulQA (0-shot) | 49.4 | |
|
| Winogrande (5-shot) | 69.77 | |
|
| GSM8K (5-shot) | 3.03 | |
|
| DROP (3-shot) | 17.45 | |
|
|
