README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - mlabonne/Daredevil-7B
  - Rakuten/RakutenAI-7B-chat
base_model:
  - mlabonne/Daredevil-7B
  - Rakuten/RakutenAI-7B-chat
language:
  - ja
model-index:
  - name: RedDevil-7B
    results:
      - task:
          type: text-generation
        dataset:
          name: ai2_arc
          type: ai2_arc
        metrics:
          - name: AI2 Reasoning Challenge (25-Shot)
            type: AI2 Reasoning Challenge (25-Shot)
            value: 67.58
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard

RedDevil-7B

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

• mlabonne/Daredevil-7B
• Rakuten/RakutenAI-7B-chat

🧩 Configuration

slices:
  - sources:
      - model: mlabonne/Daredevil-7B
        layer_range: [0, 32]
      - model: Rakuten/RakutenAI-7B-chat
        layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/Daredevil-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 = "yusukewm/RedDevil-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"])