deepseek-7b-math-code-CE-ep1-lr0001-10percent

Merged Model using LLM-AdaMerge (parameter_wise)

This model was created by merging multiple fine-tuned models using the LLM-AdaMerge approach with parameter_wise merging.

Merge Details

• Merge Type: parameter_wise
• Base Model: deepseek-ai/deepseek-coder-7b-base-v1.5
• Number of Models Merged: 2
• Models Merged: math, code
• Final Training Loss: N/A
• Training Epochs: 0

Lambda Coefficients

The following lambda coefficients were learned during training:

Parameter-wise Lambdas

This model uses parameter-wise lambda coefficients. Total parameters with individual lambdas: 273

See the uploaded learned_lambdas.json file for detailed parameter-wise coefficients.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("your-username/model-name")
tokenizer = AutoTokenizer.from_pretrained("your-username/model-name")

# Use the model
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))

Training Configuration

See the uploaded training_config.json file for detailed training configuration.

Citation

If you use this model, please cite the LLM-AdaMerge paper:

@article{llmadamerge2024,
  title={LLM-AdaMerge: Adaptive Model Merging for Large Language Models},
  author={...},
  year={2024}
}