arxiv:2508.18255
Jeffrey Quesnelle PRO
emozilla
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
Efficient Pre-Training with Token Superposition updated a model 3 months ago
NousResearch/Kimi-K2-Thinking-Alternate-Tokenizer published a model 4 months ago
PsycheFoundation/moe-10b-a1b-initOrganizations
models 92
emozilla/consilience-v1-40b-mitchell-init
Text Generation • Updated • 4
emozilla/llama3-8b-dcp-default_tt-init
Updated
emozilla/Llama-3.1-405B-DCP
Updated
emozilla/Llama-3.1-70B-DCP
Updated
emozilla/Llama-3.1-8B-DCP
Updated
emozilla/llama2-15b-gqa-init
Text Generation • Updated • 3
emozilla/llama2-1.1b-gqa-init
Text Generation • Updated • 3
emozilla/llama2-15b-init
Text Generation • Updated • 2
emozilla/llama2-1.2b-nanotron-init
Updated • 2
emozilla/llama2-1.2b-init-6
Text Generation • Updated • 1
datasets 53
emozilla/Hermes-3-Preprocessed-Llama3-2samples
Viewer • Updated • 2 • 10
emozilla/Hermes-3-Preprocessed-Llama3-100samples
Viewer • Updated • 100 • 7 • 1
emozilla/Hermes-3-Preprocessed-Llama3
Viewer • Updated • 91.1k • 15 • 1
emozilla/dolma-v1_7-30B-tokenized-llama2-nanoset
Updated • 92 • 1
emozilla/fineweb-10bt-tokenized-datatrove-llama2
Updated • 225 • 3
emozilla/fineweb-350bt-tokenized-datatrove-llama2
Updated • 276
emozilla/dolma-v1_7-305B-tokenized-llama2-nanoset
Updated • 109
emozilla/proofpile-test-tokenized-llama3
Viewer • Updated • 46.3k • 64
emozilla/PaulGrahamEssays
Viewer • Updated • 49 • 30
emozilla/dolma-v1_7-cc_en_head
Viewer • Updated • 475M • 1.23k • 1