AI & ML interests
None yet
Organizations
r-takahashi/llama-h1024-l6-90m-stacked-ba-half-2
0.2B • Updated r-takahashi/llama-h1024-l6-90m-ba-full
0.2B • Updated r-takahashi/llama-h1024-l4-60m-ba-full
0.2B • Updated r-takahashi/llama-h1024-l3-45m-ba-half-1
0.2B • Updated r-takahashi/llama-h1024-l8-120m-stacked-ba-half-2
0.2B • Updated r-takahashi/llama-h1024-l8-120m-ba-full
0.2B • Updated r-takahashi/llama-h1024-l4-60m-ba-half-1
0.2B • Updated r-takahashi/llama-h1024-l10-150m-stacked-ba-half-2
0.3B • Updated r-takahashi/llama-h1024-l10-150m-ba-full
0.3B • Updated r-takahashi/llama-h1024-l5-75m-ba-half-1
0.2B • Updated r-takahashi/llama-h512-l2-7_6m-ba-half-1
60.6M • Updated r-takahashi/llama-h512-l2-7_6m-stacked-ba-half-2
60.6M • Updated r-takahashi/llama-h512-l2-7_6m-ba-full
60.6M • Updated r-takahashi/llama-h512-l1-3_8m-ba-half-1
56.8M • Updated r-takahashi/llama-h512-l1-3_8m-ba-full
56.8M • Updated r-takahashi/llama-h512-l1-3_8m-ba-quarter-1
56.8M • Updated r-takahashi/llama-h512-l2-7_6m-ba-quarter-1
60.6M • Updated r-takahashi/llama-h512-l2-7_6m-stacked-ba-eighth-2
60.6M • Updated r-takahashi/llama-h512-l1-3_8m-ba-eighth-1
56.8M • Updated r-takahashi/llama-h1024-l2-30m-stacked-ba-eighth-2
0.1B • Updated r-takahashi/llama-h1024-l2-30m-ba-quarter-1
0.1B • Updated r-takahashi/llama-h1024-l1-15m-ba-eighth-1
0.1B • Updated r-takahashi/llama-h1024-l1-15m-ba-full
0.1B • Updated r-takahashi/llama-h512-l8-30m-stacked-ba-half-2
83.4M • Updated r-takahashi/llama-h512-l4-15m-stacked-ba-quarter-2
68.2M • Updated r-takahashi/llama-h512-l4-15m-ba-half-1
68.2M • Updated r-takahashi/llama-h512-l8-30m-ba-full
83.4M • Updated r-takahashi/llama-h512-l4-15m-ba-full
68.2M • Updated r-takahashi/llama-h768-l2-17m-stacked-ba-half-2
96.5M • Updated r-takahashi/llama-h768-l1-8_5m-ba-half-1
88M • Updated