Commit
•
490344b
1
Parent(s):
9023d20
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Setiaku/Stheno-v3.2
|
| 5 |
+
- Squish42/bluemoon-fandom-1-1-rp-cleaned
|
| 6 |
+
- openerotica/freedom-rp
|
| 7 |
+
- MinervaAI/Aesir-Preview
|
| 8 |
+
- jeiku/JeikuL3v2
|
| 9 |
+
- ResplendentAI/Sissification_Hypno_1k
|
| 10 |
+
- ResplendentAI/Synthetic_Soul_1k
|
| 11 |
+
- ResplendentAI/theory_of_mind_fixed_output
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
base_model: ResplendentAI/Nymph_8B
|
| 15 |
+
tags:
|
| 16 |
+
- not-for-all-audiences
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# QuantFactory/Nymph_8B-GGUF
|
| 21 |
+
This is quantized version of [ResplendentAI/Nymph_8B](https://huggingface.co/ResplendentAI/Nymph_8B?not-for-all-audiences=true) created using llama.cpp
|
| 22 |
+
|
| 23 |
+
# Model Description
|
| 24 |
+
|
| 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.
|