fnlp
/

Llama-2-7B-MLA-d_kv_32

Text Generation

Model card Files Files and versions Community

Research Paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs"

Downloads last month: 11

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for fnlp/Llama-2-7B-MLA-d_kv_32

Base model

meta-llama/Llama-2-7b-hf

Finetuned

(780)

this model

Dataset used to train fnlp/Llama-2-7B-MLA-d_kv_32

Collection including fnlp/Llama-2-7B-MLA-d_kv_32

MHA2MLA

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs" • 17 items • Updated 5 days ago