Commit
•
f6e9271
1
Parent(s):
ce60c74
Update README.md (#2)
Browse files- Update README.md (2540212429b03ab204bd1c958fce1c315a5fa316)
Co-authored-by: Sica Rius <SicariusSicariiStuff@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -21,6 +21,8 @@ Nymph 8B
|
|
| 21 |
|
| 22 |
GGUF here: https://huggingface.co/mradermacher/Nymph_8B-i1-GGUF
|
| 23 |
|
|
|
|
|
|
|
| 24 |
Nymph is the culmination of everything I have learned with the T-series project. This model aims to be a unique and full featured RP juggernaut.
|
| 25 |
|
| 26 |
The finetune incorporates 1.6 Million tokens of RP data sourced from Bluemoon, FreedomRP, Aesir-Preview, and Claude Opus logs. I made sure to use the multi-turn sharegpt datasets this time instead of alpaca conversions. I have also included three of my personal datasets. The final touch is an ORPO based upon Openhermes Roleplay preferences.
|
|
|
|
| 21 |
|
| 22 |
GGUF here: https://huggingface.co/mradermacher/Nymph_8B-i1-GGUF
|
| 23 |
|
| 24 |
+
- Mobile (ARM): [Q4_0_X_X](https://huggingface.co/SicariusSicariiStuff/ResplendentAI_Nymph_8B_ARM)
|
| 25 |
+
|
| 26 |
Nymph is the culmination of everything I have learned with the T-series project. This model aims to be a unique and full featured RP juggernaut.
|
| 27 |
|
| 28 |
The finetune incorporates 1.6 Million tokens of RP data sourced from Bluemoon, FreedomRP, Aesir-Preview, and Claude Opus logs. I made sure to use the multi-turn sharegpt datasets this time instead of alpaca conversions. I have also included three of my personal datasets. The final touch is an ORPO based upon Openhermes Roleplay preferences.
|