Strangemerges 17 7B Dare Ties

🚀 StrangeMerges_17-7B-dare_ties

StrangeMerges_17-7B-dare_ties是一個通過合併多個模型得到的模型。它藉助LazyMergekit工具，將不同模型的優勢融合，為文本生成任務提供了更強大的能力。

🚀 快速開始

安裝依賴

!pip install -qU transformers accelerate

代碼示例

from transformers import AutoTokenizer
import transformers
import torch

model = "Gille/StrangeMerges_17-7B-dare_ties"
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

StrangeMerges_17-7B-dare_ties模型通過合併以下兩個模型構建而成：

• Gille/StrangeMerges_16-7B-slerp
• Gille/StrangeMerges_12-7B-slerp

📦 安裝指南

使用前需要安裝transformers和accelerate庫，可以使用以下命令進行安裝：

!pip install -qU transformers accelerate

💻 使用示例

基礎用法

from transformers import AutoTokenizer
import transformers
import torch

model = "Gille/StrangeMerges_17-7B-dare_ties"
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"])

📚 詳細文檔

🧩 配置信息

models:
  - model: Gille/StrangeMerges_16-7B-slerp
    # no parameters necessary for base model
  - model: Gille/StrangeMerges_16-7B-slerp
    parameters:
      density: 0.5
      weight: 0.4
  - model: Gille/StrangeMerges_12-7B-slerp
    parameters:
      density: 0.5
      weight: 0.6
merge_method: dare_ties
base_model: Gille/StrangeMerges_16-7B-slerp
parameters:
  normalize: true
dtype: float16

Open LLM Leaderboard評估結果

詳細結果可查看此處

📄 許可證

本項目採用Apache-2.0許可證。