qikp/tokenizer-noises
36.9 MB
🔄 In a Training Loop
Charles
qikp
AI & ML interests
Training smaller models and fighting tooth and nail against underfitting.
Recent Activity
updated a model about 18 hours ago
qikp/tiny-random-Qwen4-Exp_Qwen3.8-Flash-Next published a model about 18 hours ago
qikp/tiny-random-Qwen4-Exp_Qwen3.8-Flash-Next liked a model 2 days ago
Qwen/Qwen3.8-Flash-NextOrganizations
None yet
models 94
qikp/tiny-random-Qwen4-Exp_Qwen3.8-Flash-Next
Text Generation • 31.1M • Updated
qikp/Qwen3.5-0.8B-Base-MTP-GGUF
Text Generation • 0.3B • Updated • 127
qikp/MiniCPM5-1B-Qwenified-GGUF
Text Generation • 1B • Updated • 164
qikp/MiniCPM5-1B-Qwenified
Text Generation • 1B • Updated • 250
qikp/flan-t5-small-Q8_0-GGUF
77M • Updated • 111
qikp/kite-67-12m
Text Generation • 12.1M • Updated • 360
qikp/LFM2.5-230M-Thinking-v2-GGUF
Text Generation • 0.2B • Updated • 159
qikp/LFM2.5-230M-Thinking-v2
Text Generation • 0.2B • Updated • 42
qikp/kite-6.6-12m
Text Generation • 12.1M • Updated • 27
qikp/SmolLM2-135M-Instruct-Qwenified-GGUF
Text Generation • 0.1B • Updated • 26
datasets 77
qikp/ms_marco-passages-v2.1-microsupra
Viewer • Updated • 503k • 61
qikp/ms_marco-passages-v2.1
Viewer • Updated • 503k • 48
qikp/ms_marco-passages-microsupra
Viewer • Updated • 79.7k • 58
qikp/ms_marco-passages
Viewer • Updated • 79.7k • 50
qikp/everyday-conversations-fused
Viewer • Updated • 2.38k • 94
qikp/ultrafineweb-filtered-pika-5
Viewer • Updated • 100k • 30
qikp/ultrafineweb-filtered
Viewer • Updated • 100k • 23
qikp/aya-english
Viewer • Updated • 3.94k • 26
qikp/wikipedia-2-paragraphs
Viewer • Updated • 100k • 30
qikp/small-data-4-pika-5
Viewer • Updated • 100k • 27