Active filters: Lanni-ni
Lanni-ni/transformer_babylm_10m_2layer
Text Generation
• 27.4M • Updated • 21
Lanni-ni/alibi_babylm_10m_2layer
Text Generation
• 27.4M • Updated • 45
Lanni-ni/dynamic_alibi_babylm_10m_2layer
Text Generation
• 27.4M • Updated • 42
Lanni-ni/forgetting_babylm_10m_2layer
Text Generation
• 27.4M • Updated • 20
Lanni-ni/stickbreaking_babylm_10m_2layer
Text Generation
• 27.8M • Updated • 17
Lanni-ni/hard_2gram_babylm_10m_2layer
Text Generation
• 15M • Updated • 263
Lanni-ni/hard_3gram_babylm_10m_2layer
Text Generation
• 15M • Updated • 23
Lanni-ni/hard_5gram_babylm_10m_2layer
Text Generation
• 15M • Updated • 32
Lanni-ni/transformer_pile_2layer
Text Generation
• 27.4M • Updated • 24
Lanni-ni/alibi_pile_2layer
Text Generation
• 27.4M • Updated • 45
Lanni-ni/transformer_babylm_10m_4layer
Text Generation
• 45.7M • Updated • 20
Lanni-ni/alibi_babylm_10m_4layer
Text Generation
• 45.7M • Updated • 51
Lanni-ni/dynamic_alibi_babylm_10m_4layer
Text Generation
• 45.7M • Updated • 36
Lanni-ni/forgetting_babylm_10m_4layer
Text Generation
• 45.7M • Updated • 24
Lanni-ni/stickbreaking_babylm_10m_4layer
Text Generation
• 48.1M • Updated • 19
Lanni-ni/hard_2gram_babylm_10m_4layer
Text Generation
• 28.8M • Updated • 30
Lanni-ni/hard_3gram_babylm_10m_4layer
Text Generation
• 28.8M • Updated • 34
Lanni-ni/hard_5gram_babylm_10m_4layer
Text Generation
• 28.8M • Updated • 21
Lanni-ni/transformer_babylm_100m_2layer
Text Generation
• 27.4M • Updated • 24
Lanni-ni/alibi_babylm_100m_2layer
Text Generation
• 27.4M • Updated • 48
Lanni-ni/dynamic_alibi_babylm_100m_2layer
Text Generation
• 27.4M • Updated • 40
Lanni-ni/forgetting_babylm_100m_2layer
Text Generation
• 27.4M • Updated • 21
Lanni-ni/stickbreaking_babylm_100m_2layer
Text Generation
• 27.8M • Updated • 18
Lanni-ni/hard_2gram_babylm_100m_2layer
Text Generation
• 15M • Updated • 262
Lanni-ni/hard_3gram_babylm_100m_2layer
Text Generation
• 15M • Updated • 266
Lanni-ni/hard_5gram_babylm_100m_2layer
Text Generation
• 15M • Updated • 32
Lanni-ni/transformer_babylm_100m_4layer
Text Generation
• 45.7M • Updated • 22
Lanni-ni/alibi_babylm_100m_4layer
Text Generation
• 45.7M • Updated • 43
Lanni-ni/dynamic_alibi_babylm_100m_4layer
Text Generation
• 45.7M • Updated • 45
Lanni-ni/forgetting_babylm_100m_4layer
Text Generation
• 45.7M • Updated • 20