Update README.md
Browse files
README.md
CHANGED
|
@@ -1,22 +1,62 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
-
- text-generation-inference
|
| 5 |
-
- transformers
|
| 6 |
-
- unsloth
|
| 7 |
-
- mistral
|
| 8 |
- trl
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
-
# Uploaded model
|
| 15 |
|
| 16 |
-
-
|
| 17 |
-
-
|
| 18 |
-
-
|
|
|
|
| 19 |
|
| 20 |
-
|
|
|
|
|
|
|
| 21 |
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model:
|
| 5 |
+
- HuggingFaceH4/zephyr-7b-beta
|
| 6 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- trl
|
| 8 |
+
- sft
|
| 9 |
+
- unsloth
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: ZoraBetaA1
|
| 13 |
+
results: []
|
| 14 |
language:
|
| 15 |
- en
|
| 16 |
---
|
| 17 |
+
Support us On **KO-FI**
|
| 18 |
+
[](https://ko-fi.com/J3J61D8NHV)
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
**ZoraBetaA family**
|
| 23 |
+
# ZoraBetaA2 - EmpressOfRoleplay
|
| 24 |
+
- ZoraBetaA2 is Our Brand new AI Model, finetuned from Our A1 model using [Iris-Uncensored-Reformat-R2](https://huggingface.co/datasets/N-Bot-Int/Iris-Uncensored-Reformat-R2?not-for-all-audiences=true) with higher step,
|
| 25 |
+
ZoraBetaA2 showcase a Strong Roleplaying Capability With an Even Stronger Finetuned Bias toward Roleplaying Using **Zephyr Beta 7B**,
|
| 26 |
+
ZoraBetaA2 also Shows a Great Roleplaying Capabilities, Without Hallucinating Much Unlike MistThena7B Finetuned Using Mistral 7b v0.1,
|
| 27 |
+
ZoraBetaA2 Is A Much Biased To Roleplay AI Model, compared the A1 model, due to this, the A2 Model failed at Other Purpose Beyond Roleplaying
|
| 28 |
+
This New Architecture allow us To Increase Roleplaying capabilities without Doing everything from scratch as **Zephyr Beta** has a Strong RP foundation already,
|
| 29 |
+
Leading us to Scaffolding on this Architecture And Increasing Roleplaying capabilities further.
|
| 30 |
+
|
| 31 |
+
- ZoraBetaA2 contains Cleaned Dataset, however its still relatively Unstable so please Report any issues found through our email
|
| 32 |
+
[nexus.networkinteractives@gmail.com](nexus.networkinteractives@gmail.com)
|
| 33 |
+
about any overfitting, or improvements for the future Models
|
| 34 |
+
Once again feel free to Modify the LORA to your likings, However please consider Adding this Page
|
| 35 |
+
for credits and if you'll increase its **Dataset**, then please handle it with care and ethical considerations
|
| 36 |
+
|
| 37 |
+
- ZoraBetaA2 is
|
| 38 |
+
- **Developed by:** N-Bot-Int
|
| 39 |
+
- **License:** apache-2.0
|
| 40 |
+
- **Parent Model from model:** HuggingFaceH4/zephyr-7b-beta
|
| 41 |
+
- **Dataset Combined Using:** UltraDatasetCleanerAndMoshpit-R1(Propietary Software)
|
| 42 |
+
|
| 43 |
+
- # Notice
|
| 44 |
+
- **For a Good Experience, Please use**
|
| 45 |
+
- Low temperature 1.5, min_p = 0.1 and max_new_tokens = 128
|
| 46 |
|
|
|
|
| 47 |
|
| 48 |
+
- # Detail card:
|
| 49 |
+
- Parameter
|
| 50 |
+
- 7 Billion Parameters
|
| 51 |
+
- (Please visit your GPU Vendor if you can Run 3B models)
|
| 52 |
|
| 53 |
+
- Training
|
| 54 |
+
- 300 Steps from
|
| 55 |
+
Iris-Dataset-Reformat-R1
|
| 56 |
|
| 57 |
+
- Finetuning tool:
|
| 58 |
+
- Unsloth AI
|
| 59 |
+
- This Zephyr model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 60 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
| 61 |
+
- Fine-tuned Using:
|
| 62 |
+
- Google Colab
|