| license: apache-2.0 | |
| datasets: | |
| - HuggingFaceTB/smollm-corpus | |
| base_model: | |
| - meta-llama/Llama-2-7b-hf | |
| pipeline_tag: text-generation | |
| **Research Paper** ["Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs"](https://arxiv.org/abs/2502.14837) |