fnlp/SmolLM-135M-MLA-d_kv_8-refactor
Text Generation
•
0.1B
•
Updated
•
8
MHA2MLA-refactor
The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs"
-
-
fnlp/SmolLM-135M-MLA-d_kv_32-refactor
Text Generation • 0.1B • Updated • 4 -
fnlp/SmolLM-135M-MLA-d_kv_16-refactor
Text Generation • 0.1B • Updated -
fnlp/SmolLM-360M-MLA-d_kv_8-refactor
Text Generation • 0.3B • Updated • 1 -
fnlp/SmolLM-360M-MLA-d_kv_16-refactor
Text Generation • 0.3B • Updated -
fnlp/SmolLM-360M-MLA-d_kv_32-refactor
Text Generation • 0.4B • Updated • 1 -
fnlp/smollm1-1B7-d_kv_8-refactor
Text Generation • 2B • Updated -
fnlp/smollm1-1B7-d_kv_16-refactor
Text Generation • 2B • Updated -
fnlp/smollm1-1B7-d_kv_32-refactor
Text Generation • 2B • Updated -
fnlp/llama2-7B-d_kv_16-refactor
Text Generation • 6B • Updated -
fnlp/llama2-7B-d_kv_32-refactor
Text Generation • 6B • Updated -
fnlp/llama2-7B-d_kv_64-refactor
Text Generation • 7B • Updated