AI & ML interests
None yet
Organizations
None yet
Lanni-ni/stickbreaking_4_6_384_pile
Text Generation
• 48.1M • Updated Lanni-ni/geometric_4_6_384_pile
Text Generation
• 45.7M • Updated Lanni-ni/transformer_4_6_384_pile
Text Generation
• 45.7M • Updated • 1
Lanni-ni/forgetting_gate_4_6_384_babylm
Text Generation
• 45.7M • Updated Lanni-ni/stickbreaking_4_6_384_babylm
Text Generation
• 48.1M • Updated Lanni-ni/geometric_4_6_384_babylm
Text Generation
• 45.7M • Updated • 1
Lanni-ni/alibi_4_6_384_babylm
Text Generation
• 45.7M • Updated Lanni-ni/transformer_4_6_384_babylm
Text Generation
• 45.7M • Updated Lanni-ni/hard_5gram_4_6_384_babylm
Text Generation
• 28.8M • Updated Lanni-ni/hard_3gram_4_6_384_babylm
Text Generation
• 28.8M • Updated Lanni-ni/hard_2gram_4_6_384_babylm
Text Generation
• 28.8M • Updated Lanni-ni/dynamic_alibi_4_6_384_babylm
26.8M • Updated Lanni-ni/dynamic_alibi_babylm_4_6_384
26.8M • Updated Lanni-ni/sliding_window_4_6_384_w1
Lanni-ni/stickbreaking_4_6_384
48.1M • Updated Lanni-ni/geometric_4_6_384
45.7M • Updated Lanni-ni/transformer_4_6_384
Text Generation
• 45.7M • Updated • 1
Text Generation
• 45.7M • Updated Lanni-ni/dynamic_alibi_4_6_384
Text Generation
• 26.8M • Updated Lanni-ni/stickbreaking_4_6_384_
Text Generation
• 48.1M • Updated • 15
Lanni-ni/geometric_4_6_384_
Text Generation
• 45.7M • Updated Lanni-ni/forgetting_gate_4_6_384_
Text Generation
• 45.7M • Updated Text Generation
• 45.7M • Updated Lanni-ni/transformer_4_6_384_
Text Generation
• 45.7M • Updated • 3
Lanni-ni/transformer_2_4_256_softmax
Text Generation
• 27.4M • Updated • 1
Lanni-ni/alibi_2_4_256_softmax
Text Generation
• 27.4M • Updated • 1
Lanni-ni/transformer_12_12_768_softmax
Text Generation
• 0.2B • Updated • 4
Lanni-ni/alibi_12_12_768_softmax
Text Generation
• 0.2B • Updated • 1
Lanni-ni/transformer_12_12_768_
Text Generation
• 0.2B • Updated Lanni-ni/transformer_no_rope_
Text Generation
• 45.7M • Updated