Commit
•
4dc531a
1
Parent(s):
b5d5673
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# Opus-Samantha-Llama-3-8B
|
|
@@ -8,6 +10,9 @@ Opus-Samantha-Llama-3-8B is a SFT model made with [AutoSloth](https://colab.rese
|
|
| 8 |
|
| 9 |
Trained on 1xL4 for 1 hour
|
| 10 |
|
|
|
|
|
|
|
|
|
|
| 11 |
## Process
|
| 12 |
|
| 13 |
- Original Model: [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b)
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- macadeliccc/opus_samantha
|
| 5 |
---
|
| 6 |
|
| 7 |
# Opus-Samantha-Llama-3-8B
|
|
|
|
| 10 |
|
| 11 |
Trained on 1xL4 for 1 hour
|
| 12 |
|
| 13 |
+
_model is curretly very nsfw. uneven distribution of subjects in dataset. will be back with v2_
|
| 14 |
+
|
| 15 |
+
|
| 16 |
## Process
|
| 17 |
|
| 18 |
- Original Model: [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b)
|