RichardErkhov/core-3_-_kuno-royale-7B-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

kuno-royale-7B - bnb 8bits

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

Original model description:

license: cc-by-nc-2.0 tags: - merge - mergekit - lazymergekit - SanjiWatsuki/Kunoichi-DPO-v2-7B - eren23/ogno-monarch-jaskier-merge-7b base_model: - SanjiWatsuki/Kunoichi-DPO-v2-7B - eren23/ogno-monarch-jaskier-merge-7b model-index: - name: kuno-royale-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: 71.76 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-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: 88.2 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-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: 65.13 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-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: 71.12 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-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: 82.32 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-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: 69.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B name: Open LLM Leaderboard

kuno-royale-7B

v2 is probably better 🤷

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-7B is a merge of the following models using LazyMergekit:

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

🧩 Configuration

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