Update README.md
Browse files
README.md
CHANGED
@@ -1 +1,15 @@
|
|
1 |
-
Dont be upsetti, here, have some spaghetti! Att: A'eala
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Dont be upsetti, here, have some spaghetti! Att: A'eala <3
|
2 |
+
|
3 |
+
<p><strong><font size="5">Information</font></strong></p>
|
4 |
+
GPT4-X-Alpasta-30b working with Oobabooga's Text Generation Webui and KoboldAI.
|
5 |
+
<p>This is an attempt at improving Open Assistant's performance as an instruct while retaining its excellent prose. The merge consists of <a href="https://huggingface.co/chansung/gpt4-alpaca-lora-30b">Chansung's GPT4-Alpaca Lora</a> and <a href="https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor">Open Assistant's native fine-tune</a>.</p>
|
6 |
+
|
7 |
+
<p><strong><font size="5">Benchmarks</font></strong></p>
|
8 |
+
|
9 |
+
<p><strong><font size="4">FP16 (These are actually 4-bit benchmarks) (Placeholder)</font></strong></p>
|
10 |
+
|
11 |
+
<strong>Wikitext2</strong>: 4.998758792877197
|
12 |
+
|
13 |
+
<strong>Ptb-New</strong>: 9.802155494689941
|
14 |
+
|
15 |
+
<strong>C4-New</strong>: 7.341384410858154
|