Darebeagle 7B

🚀 DareBeagle-7B

DareBeagle-7B 是一个融合模型，它使用 LazyMergekit 融合了以下模型，在文本生成任务中展现出了优秀的性能。

🚀 快速开始

安装依赖

!pip install -qU transformers accelerate

代码示例

from transformers import AutoTokenizer
import transformers
import torch

model = "shadowml/DareBeagle-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"])

✨ 主要特性

DareBeagle-7B 是通过融合以下两个模型得到的：

• mlabonne/NeuralBeagle14-7B
• mlabonne/NeuralDaredevil-7B

📦 安装指南

使用以下命令安装所需的库：

!pip install -qU transformers accelerate

💻 使用示例

基础用法

from transformers import AutoTokenizer
import transformers
import torch

model = "shadowml/DareBeagle-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"])

📚 详细文档

🧩 配置信息

slices:
  - sources:
      - model: mlabonne/NeuralBeagle14-7B
        layer_range: [0, 32]
      - model: mlabonne/NeuralDaredevil-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/NeuralDaredevil-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: 0.45 # fallback for rest of tensors
dtype: float16

Open LLM Leaderboard 评估结果

详细结果可查看 此处

📄 许可证

本项目采用 Apache-2.0 许可证。