AI & ML interests
None yet
Organizations
None yet
Lanni-ni/hard_5gram_pile_4layer
Text Generation
• 28.8M • Updated Lanni-ni/hard_3gram_pile_4layer
Text Generation
• 28.8M • Updated Lanni-ni/hard_2gram_pile_4layer
Text Generation
• 28.8M • Updated Lanni-ni/stickbreaking_pile_4layer
Text Generation
• 48.1M • Updated Lanni-ni/geometric_pile_4layer
Text Generation
• 45.7M • Updated Lanni-ni/forgetting_pile_4layer
Text Generation
• 45.7M • Updated Lanni-ni/dynamic_alibi_pile_4layer
Text Generation
• 45.7M • Updated Lanni-ni/alibi_pile_4layer
Text Generation
• 45.7M • Updated Lanni-ni/transformer_pile_4layer
Text Generation
• 45.7M • Updated Lanni-ni/hard_5gram_pile_2layer
Text Generation
• 15M • Updated Lanni-ni/hard_3gram_pile_2layer
Text Generation
• 15M • Updated Lanni-ni/hard_2gram_pile_2layer
Text Generation
• 15M • Updated Lanni-ni/stickbreaking_pile_2layer
Text Generation
• 27.8M • Updated Lanni-ni/geometric_pile_2layer
Text Generation
• 27.4M • Updated Lanni-ni/forgetting_pile_2layer
Text Generation
• 27.4M • Updated • 1
Lanni-ni/dynamic_alibi_pile_2layer
Text Generation
• 27.4M • Updated Lanni-ni/alibi_pile_2layer
Text Generation
• 27.4M • Updated Lanni-ni/transformer_pile_2layer
Text Generation
• 27.4M • Updated Lanni-ni/hard_5gram_babylm_100m_4layer
Text Generation
• 28.8M • Updated Lanni-ni/hard_3gram_babylm_100m_4layer
Text Generation
• 28.8M • Updated Lanni-ni/hard_2gram_babylm_100m_4layer
Text Generation
• 28.8M • Updated Lanni-ni/stickbreaking_babylm_100m_4layer
Text Generation
• 48.1M • Updated Lanni-ni/geometric_babylm_100m_4layer
Text Generation
• 45.7M • Updated Lanni-ni/forgetting_babylm_100m_4layer
Text Generation
• 45.7M • Updated Lanni-ni/dynamic_alibi_babylm_100m_4layer
Text Generation
• 45.7M • Updated Lanni-ni/alibi_babylm_100m_4layer
Text Generation
• 45.7M • Updated Lanni-ni/transformer_babylm_100m_4layer
Text Generation
• 45.7M • Updated • 1
Lanni-ni/hard_5gram_babylm_100m_2layer
Text Generation
• 15M • Updated Lanni-ni/hard_3gram_babylm_100m_2layer
Text Generation
• 15M • Updated Lanni-ni/hard_2gram_babylm_100m_2layer
Text Generation
• 15M • Updated