Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,14 @@ It's kinda okay for sampling, but needs improvements and exposure to more synthe
|
|
| 10 |
|
| 11 |
Overall I'm extremely impressed with how well this 68 million parameter model works, and extremely disappointed with how every single AI is getting picked up after only training BERT on GPT3.5 rows of the data.
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
It's really blatant how every single AI company is using the same watermark whether knowingly or unknowingly (through LLM "incest")
|
|
|
|
| 10 |
|
| 11 |
Overall I'm extremely impressed with how well this 68 million parameter model works, and extremely disappointed with how every single AI is getting picked up after only training BERT on GPT3.5 rows of the data.
|
| 12 |
|
| 13 |
+
We tested these models all of which worked:
|
| 14 |
+
|
| 15 |
+
GPT3.5, 4, 4o
|
| 16 |
+
|
| 17 |
+
Claude Sonnet, Opus
|
| 18 |
+
|
| 19 |
+
Wizard LM 2
|
| 20 |
+
|
| 21 |
+
Gemini 1.5 Pro
|
| 22 |
+
|
| 23 |
It's really blatant how every single AI company is using the same watermark whether knowingly or unknowingly (through LLM "incest")
|