README.md

---
tags:
- merge
- parameter_wise
- llm-adamerge
base_model: mistralai/Mistral-7B-v0.1
---

# 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**: mistralai/Mistral-7B-v0.1
- **Number of Models Merged**: 3
- **Models Merged**: instruct, 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: 291


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

## Usage

```python
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:

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