You can deploy this model and start earning money today!

RichardErkhov/
core-3_-_kuno-royale-v2-7b-gguf

Name: core-3_-_kuno-royale-v2-7b-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

kuno-royale-v2-7b - GGUF

Model creator: https://huggingface.co/core-3/
Original model: https://huggingface.co/core-3/kuno-royale-v2-7b/

Name	Quant method	Size
kuno-royale-v2-7b.Q2_K.gguf	Q2_K	2.53GB
kuno-royale-v2-7b.IQ3_XS.gguf	IQ3_XS	2.81GB
kuno-royale-v2-7b.IQ3_S.gguf	IQ3_S	2.96GB
kuno-royale-v2-7b.Q3_K_S.gguf	Q3_K_S	2.95GB
kuno-royale-v2-7b.IQ3_M.gguf	IQ3_M	3.06GB
kuno-royale-v2-7b.Q3_K.gguf	Q3_K	3.28GB
kuno-royale-v2-7b.Q3_K_M.gguf	Q3_K_M	3.28GB
kuno-royale-v2-7b.Q3_K_L.gguf	Q3_K_L	3.56GB
kuno-royale-v2-7b.IQ4_XS.gguf	IQ4_XS	3.67GB
kuno-royale-v2-7b.Q4_0.gguf	Q4_0	3.83GB
kuno-royale-v2-7b.IQ4_NL.gguf	IQ4_NL	3.87GB
kuno-royale-v2-7b.Q4_K_S.gguf	Q4_K_S	3.86GB
kuno-royale-v2-7b.Q4_K.gguf	Q4_K	4.07GB
kuno-royale-v2-7b.Q4_K_M.gguf	Q4_K_M	4.07GB
kuno-royale-v2-7b.Q4_1.gguf	Q4_1	4.24GB
kuno-royale-v2-7b.Q5_0.gguf	Q5_0	4.65GB
kuno-royale-v2-7b.Q5_K_S.gguf	Q5_K_S	4.65GB
kuno-royale-v2-7b.Q5_K.gguf	Q5_K	4.78GB
kuno-royale-v2-7b.Q5_K_M.gguf	Q5_K_M	4.78GB
kuno-royale-v2-7b.Q5_1.gguf	Q5_1	5.07GB
kuno-royale-v2-7b.Q6_K.gguf	Q6_K	5.53GB
kuno-royale-v2-7b.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-2.0 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 model-index:
name: kuno-royale-v2-7b results:
- task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
  - type: acc_norm value: 72.01 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v2-7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
  - type: acc_norm value: 88.15 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v2-7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
  - type: acc value: 65.07 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v2-7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
  - type: mc2 value: 71.1 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v2-7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
  - type: acc value: 82.24 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v2-7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 70.2 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v2-7b name: Open LLM Leaderboard

kuno-royale-v2-7b

An attempt to further strengthen the roleplaying prose of SanjiWatsuki/Kunoichi-DPO-v2-7B using eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO, a high-scorer for 7B models on the Open LLM Leaderboard.

Personal RP tests prove promising, and meaningless leaderboard metrics have improved vs SanjiWatsuki/Kunoichi-DPO-v2-7B.

Some GGUF quants available here.

Works well with Silly Tavern Noromaid template recommended by SanjiWatsuki for Kunoichi-7B: Context, Instruct

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	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:

🧩 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"])

RichardErkhov/core-3_-_kuno-royale-v2-7b-gguf