Neural 4 Maths 7b

🚀 Neural-4-Maths-7b

Neural-4-Maths-7b is a merged model that combines the strengths of multiple base models. It uses LazyMergekit to integrate several pre - trained models, aiming to provide enhanced performance in relevant tasks.

✨ Features

• Model Merging: Merges multiple high - quality models to potentially offer better performance.
• Flexible Configuration: Allows for customizing parameters such as density and weight during the merging process.

📦 Installation

!pip install -qU transformers accelerate

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/Neural-4-Maths-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"])

📚 Documentation

🧩 Configuration

models:
  - model: Kukedlc/NeuralSirKrishna-7b
    # No parameters necessary for base model
  - model: liminerity/M7-7b
    parameters:
      density: 0.66
      weight: 0.2
  - model: MTSAIR/multi_verse_model
    parameters:
      density: 0.66
      weight: 0.2
  - model: Kukedlc/NeuralSirKrishna-7b
    parameters:
      density: 0.66
      weight: 0.2
  - model: Kukedlc/NeuralMaths-Experiment-7b
    parameters:
      density: 0.44
      weight: 0.2
  - model: Kukedlc/Neural4gsm8k
    parameters:
      density: 0.44
      weight: 0.2
merge_method: dare_ties
base_model: Kukedlc/NeuralSirKrishna-7b
parameters:
  int8_mask: true
dtype: bfloat16

📄 License

This project is licensed under the apache-2.0 license.