metadata

language:
  - ja
tags:
  - merge
  - mergekit
  - lazymergekit
  - SakanaAI/EvoLLM-JP-A-v1-7B
  - stabilityai/japanese-stablelm-base-gamma-7b
base_model:
  - SakanaAI/EvoLLM-JP-A-v1-7B
  - stabilityai/japanese-stablelm-base-gamma-7b

🌲 Hinoki-Sak-Sta-slerp-7B

Hinoki-Sak-Sta-slerp-7B is a merge of the following models using the LazyMergekit of Maxime Labonne powered by MergeKit of Arcee AI:

SakanaAI/EvoLLM-JP-A-v1-7B (Base model)
stabilityai/japanese-stablelm-base-gamma-7b

💻 Configuration

slices:
  - sources:
      - model: SakanaAI/EvoLLM-JP-A-v1-7B
        layer_range: [0, 32]
      - model: stabilityai/japanese-stablelm-base-gamma-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: SakanaAI/EvoLLM-JP-A-v1-7B
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 for HuggingFace

from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import pipeline
import torch

model_name = "AkimfromParis/Hinoki-Sak-Sta-slerp-7B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, pad_token_id=tokenizer.eos_token_id)

messages = [
    {"role": "system","content": "あなたは誠実で優秀な日本人のアシスタントです。以下のトピックに関する詳細な情報を提供してください。"},
    {"role": "user", "content": "大谷翔平選手は誰ですか？"},
    ]
print(pipe(messages, max_new_tokens=512)[0]['generated_text'][-1])

🔖 Citation

@misc{goddard2024arcee,
  title={Arcee's MergeKit: A Toolkit for Merging Large Language Models},
  author={Goddard, Charles and Siriwardhana, Shamane and Ehghaghi, Malikeh and Meyers, Luke and Karpukhin, Vlad and Benedict, Brian and McQuade, Mark and Solawetz, Jacob},
  journal={arXiv preprint arXiv:2403.13257},
  year={2024}
}

arxiv.org/abs/2403.13257