license: llama3.1
Llama 3.1 Devilish
This model is an experimental Llama 3.1-based merge, inspired by the approach used in mlabonne/Daredevil-8B. It combines top-performing MMLU-Pro models using the 8.03 billion parameter Llama architecture from the Open LLM Leaderboard as of January 21, 2025.
Model Details
- Architecture: Llama 3.1 (8.03B parameters)
- Training: Merged from top MMLU-Pro models, with additional SFT
- Release Date: January 21, 2025
Key Features
- Merged Architecture: Combines high-performing MMLU-Pro models to enhance overall capabilities.
- Llama 3 Compatibility: Additional Supervised Fine-Tuning (SFT) ensures adherence to Llama 3 prompt format.
- SFT Dataset: agentlans/crash-course dataset (1200 row configuration) for supervised fine-tuning in LLaMA-Factory.
- Fine-Tuning Approach:
- 1 epoch training
- Rank 4 LoRA
- Alpha = 4
- rslora
Merge Configuration
The model was created using mergekit with the following merge configuration:
models:
- model: DreadPoor/LemonP-8B-Model_Stock
parameters:
density: 0.6
weight: 0.16
- model: Youlln/1PARAMMYL-8B-ModelStock
parameters:
density: 0.6
weight: 0.13
- model: jaspionjader/f-2-8b
parameters:
density: 0.6
weight: 0.10
- model: Etherll/SuperHermes
parameters:
density: 0.6
weight: 0.08
merge_method: dare_ties
base_model: meta-llama/Llama-3.1-8B
dtype: bfloat16
Usage and Limitations
This experimental model is designed for research and development purposes. Users should be aware of potential biases and limitations inherent in language models. Always validate outputs and use the model responsibly.
Future Work
Further evaluation and fine-tuning may be necessary to optimize performance across various tasks. Researchers are encouraged to build upon this experimental merge to advance the capabilities of Llama-based models.