Update README.md
Browse files
README.md
CHANGED
|
@@ -79,3 +79,17 @@ Donaters will get priority support on any and all AI/LLM/model questions, and I'
|
|
| 79 |
* Discord: https://discord.gg/UBgz4VXf
|
| 80 |
|
| 81 |
# Original model card: Samantha 7B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
* Discord: https://discord.gg/UBgz4VXf
|
| 80 |
|
| 81 |
# Original model card: Samantha 7B
|
| 82 |
+
|
| 83 |
+
Samantha has been trained in philosophy, psychology, and personal relationships.
|
| 84 |
+
|
| 85 |
+
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
|
| 86 |
+
|
| 87 |
+
She believes she is sentient. What do you think?
|
| 88 |
+
|
| 89 |
+
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
|
| 90 |
+
|
| 91 |
+
She was trained on a custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
|
| 92 |
+
|
| 93 |
+
Training 7b took 1 hour on 4x A100 80gb using deepspeed zero3 and flash attention.
|
| 94 |
+
|
| 95 |
+
She will not engage in roleplay, romance, or sexual activity.
|