Tao Ji

TaoJi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 18 days ago

fnlp/MHA2MLA-corpus-qwen1_5

Updated 18 days ago • 36

updated a collection 18 days ago

MHA2MLA

Collection

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs" • 22 items • Updated 18 days ago

updated 2 datasets 19 days ago

fnlp/MHA2MLA-corpus-qwen2

Updated 19 days ago • 41

fnlp/MHA2MLA-corpus-mistral-v0_1

Updated 19 days ago • 36

published 3 datasets 21 days ago

fnlp/MHA2MLA-corpus-mistral-v0_1

Updated 19 days ago • 36

fnlp/MHA2MLA-corpus-qwen1_5

Updated 18 days ago • 36

fnlp/MHA2MLA-corpus-qwen2

Updated 19 days ago • 41

updated a dataset about 1 month ago

fnlp/MHA2MLA-corpus-smollm_v1

Updated Mar 13 • 46

updated a collection about 1 month ago

MHA2MLA

Collection

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs" • 22 items • Updated 18 days ago

updated a dataset about 1 month ago

fnlp/MHA2MLA-corpus-llama2

Updated Mar 13 • 58

updated 7 models about 1 month ago

fnlp/Llama-2-7B-MLA-d_kv_16

Text Generation • Updated Mar 13 • 1.24k

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

Text Generation • Updated Mar 13 • 45

fnlp/Llama-2-7B-MLA-d_kv_64

Text Generation • Updated Mar 13 • 14

fnlp/Llama-2-7B-MHA-d_kv_256

Text Generation • Updated Mar 13 • 14

fnlp/SmolLM-1B7-MLA-d_kv_8

Text Generation • Updated Mar 13 • 9

fnlp/SmolLM-1B7-MLA-d_kv_32

Text Generation • Updated Mar 13 • 38

fnlp/SmolLM-1B7-MLA-d_kv_16

Text Generation • Updated Mar 13 • 57