gigant/bytes-tokenizer
Updated
théo gigant
gigant
AI & ML interests
multimodal
Recent Activity
authored a paper 26 days ago
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation submitted a paper 27 days ago
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level SimulationOrganizations
gigant/led_tib
0.2B • Updated • 2
gigant/SmolLM-mc4-500-rawrope
Text Generation • 0.1B • Updated • 1
gigant/SmolLM-mc4-500-ropescaled
Text Generation • 0.1B • Updated • 3
gigant/SmolLM-500-rawrope
Text Generation • 0.1B • Updated • 2
gigant/SmolLM-500-ropescaled
Text Generation • 0.1B • Updated • 2
gigant/SmolLM-135M-ft-500-steps
Text Generation • 0.1B • Updated • 5
gigant/SmolLM-135M-rescaled-ft-500-steps
Text Generation • 0.1B • Updated • 3
gigant/SmolLM-135M-unjetlagged-200-steps
Updated
gigant/SmolLM-135M-full-unjetlagged-2000-steps
Updated
gigant/SmolLM-135M-full-jetlagged-200-steps
Text Generation • 0.1B • Updated • 1
gigant/SmolLM-135M-full-unjetlagged-200-steps
Text Generation • 0.1B • Updated • 1
gigant/SmolLM-135M-jetlagged-200-steps
Updated
gigant/SmolLM-135M-unjetlagged
Updated
gigant/SmolLM-135M-scaled-rope-sw
Text Generation • 0.1B • Updated • 3
gigant/flan-t5fire-small
77M • Updated • 2
gigant/graphlongt5-structural-dependency-0408
Updated • 3
gigant/longt5-0322
Updated • 2
gigant/graphlongt5-structural-0324
Updated • 3
gigant/graphlongt5-dependency-0322
Updated • 2
gigant/graphlongt5-globallocal-0322
Updated • 2
gigant/graphlongt5-structural-0320
Updated • 2
gigant/graphlongt5-dependency-0308
Updated • 2
gigant/graphlongt5-globallocal-0308
Updated • 2
gigant/longt5-0229
Updated • 2
gigant/graphlongt5-globallocal-0228
Updated • 2
gigant/graphlongt5-dependency-0228
Updated • 3
gigant/longt5-global-3epoch
Updated • 3
gigant/graph-t5-global-window-8k-longt5local
Updated • 3
gigant/graph-t5-global-window-8k-tib
Updated • 2