Strangemerges 17 7B Dare Ties

🚀 StrangeMerges_17-7B-dare_ties

StrangeMerges_17-7B-dare_ties is a merged model that combines the strengths of multiple base models. It uses the LazyMergekit technique to merge the following models:

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

✨ Features

• Model Merging: Utilizes LazyMergekit to combine multiple base models effectively.
• Text Generation: Performs well in various text generation tasks as shown in the evaluation results.

📦 Installation

To use this model, you need to install the necessary libraries. You can use the following command:

!pip install -qU transformers accelerate

💻 Usage Examples

Basic Usage

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"])

📚 Documentation

🧩 Configuration

The following is the configuration for merging the models:

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

📊 Evaluation Results

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

📄 License

This model is released under the Apache-2.0 license.