|
--- |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO |
|
base_model: |
|
- SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO |
|
license: cc-by-nc-2.0 |
|
--- |
|
|
|
 |
|
|
|
# kuno-royale-v2-7b |
|
|
|
An attempt to further strengthen the roleplaying prose of [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co./SanjiWatsuki/Kunoichi-DPO-v2-7B) using [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO](https://huggingface.co./eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO), a high-scorer for 7B models on the [Open LLM Leaderboard](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard). |
|
|
|
Personal RP tests prove promising, and meaningless leaderboard metrics have improved vs [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co./SanjiWatsuki/Kunoichi-DPO-v2-7B). |
|
|
|
Some GGUF quants available [here](https://huggingface.co./core-3/kuno-royale-v2-7b-GGUF). |
|
|
|
Works well with Silly Tavern Noromaid template recommended by [SanjiWatsuki for Kunoichi-7B](https://huggingface.co./SanjiWatsuki/Kunoichi-7B): [Context](https://files.catbox.moe/ifmhai.json), [Instruct](https://files.catbox.moe/ttw1l9.json) |
|
|
|
|Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | |
|
|-------------------|---------|-----|-----------|------|------------|------------|-------| |
|
| eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO | 76.45 | 73.12 | 89.09 | 64.80 | 77.45 | 84.77 | 69.45 | |
|
| **core-3/kuno-royale-v2-7b** | **74.80** | **72.01** | **88.15** | **65.07** | **71.10** | **82.24** | **70.20** | |
|
| [core-3/kuno-royale-7B](https://huggingface.co./core-3/kuno-royale-7B) | 74.74 | 71.76 | 88.20 | 65.13 | 71.12 | 82.32 | 69.90 |
|
| SanjiWatsuki/Kunoichi-DPO-v2-7B | 72.46 | 69.62 | 87.44 | 64.94 | 66.06 | 80.82 | 65.88 | |
|
| SanjiWatsuki/Kunoichi-7B | 72.13 | 68.69 | 87.10 | 64.90 | 64.04 | 81.06 | 67.02 | |
|
|
|
|
|
# Original LazyMergekit Card: |
|
|
|
kuno-royale-v2-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co./SanjiWatsuki/Kunoichi-DPO-v2-7B) |
|
* [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO](https://huggingface.co./eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO) |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
slices: |
|
- sources: |
|
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
layer_range: [0, 32] |
|
- model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
``` |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "core-3/kuno-royale-v2-7b" |
|
messages = [{"role": "user", "content": "What is a large language model?"}] |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
