kuno-royale-v3-7b/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
cc-by-nc-2.0	merge mergekit lazymergekit SanjiWatsuki/Kunoichi-DPO-v2-7B eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v3	SanjiWatsuki/Kunoichi-DPO-v2-7B eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v3	name results kuno-royale-v3-7b task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 71.76 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v3-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 88.23 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v3-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 65.06 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v3-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 71.13 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v3-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 82.32 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v3-7b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 70.81 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-v3-7b Open LLM Leaderboard

kuno-royale-v3-7b

Another experimental combination of eren23's ongo-monarch-jaskier merges and Kunoichi-DPO-v2-7B. Untested.

kuno-royale-v3-7b is a merge of the following models using LazyMergekit:

• SanjiWatsuki/Kunoichi-DPO-v2-7B
• eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v3

🧩 Configuration

slices:
  - sources:
      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
        layer_range: [0, 32]
      - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v3
        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

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "core-3/kuno-royale-v3-7b"
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.88
AI2 Reasoning Challenge (25-Shot)	71.76
HellaSwag (10-Shot)	88.23
MMLU (5-Shot)	65.06
TruthfulQA (0-shot)	71.13
Winogrande (5-shot)	82.32
GSM8k (5-shot)	70.81