Pretrained LLMs from scratch.
Y. Yu
PursuitOfDataScience
AI & ML interests
LLM, GPU Computing, PyTorch
Recent Activity
updated a dataset 1 day ago
PursuitOfDataScience/openmath-reasoning-minimax updated a model 11 days ago
PursuitOfDataScience/Qwen3.5-0.8B-Opus-4.6-thinking published a model 11 days ago
PursuitOfDataScience/Qwen3.5-0.8B-Opus-4.6-thinkingOrganizations
None yet
Trial & Error models for various tasks.
-
PursuitOfDataScience/roberta-large-ner
Token Classification • 0.4B • Updated -
PursuitOfDataScience/distilbert-base-cased-ner
Token Classification • 65.2M • Updated -
PursuitOfDataScience/bert-base-ner
Token Classification • 0.1B • Updated • 1 -
PursuitOfDataScience/t5-large-summary-model
0.7B • Updated • 1
Pretrained LLMs from scratch.
Trial & Error models for various tasks.
-
PursuitOfDataScience/roberta-large-ner
Token Classification • 0.4B • Updated -
PursuitOfDataScience/distilbert-base-cased-ner
Token Classification • 65.2M • Updated -
PursuitOfDataScience/bert-base-ner
Token Classification • 0.1B • Updated • 1 -
PursuitOfDataScience/t5-large-summary-model
0.7B • Updated • 1
models 27
PursuitOfDataScience/Qwen3.5-0.8B-Opus-4.6-thinking
Text Generation • 0.8B • Updated • 10 • 1
PursuitOfDataScience/Qwen3.5-0.8B-thinking
Text Generation • 0.8B • Updated • 30
PursuitOfDataScience/llama3.2-3b-thinking
Updated • 75
PursuitOfDataScience/Qwen3-0.6b-thinking
Text Generation • Updated • 12
PursuitOfDataScience/Llama-3.2-1B-GRPO
Text Generation • 1B • Updated • 7
PursuitOfDataScience/Argonne-2.0
Text Generation • 6B • Updated • 1
PursuitOfDataScience/llama3.2-1b-thinking
Text Generation • 1B • Updated • 1
PursuitOfDataScience/llama-3-2-1b-open-r1-mot-sft
Text Generation • 1B • Updated
PursuitOfDataScience/qwen2.5-0.5b-r1-dpo
Text Generation • 0.5B • Updated
PursuitOfDataScience/qwen2.5-0.5b-dpo
Text Generation • 0.5B • Updated • 2
datasets 46
PursuitOfDataScience/openmath-reasoning-minimax
Viewer • Updated • 2.68M • 176
PursuitOfDataScience/oss-code-seeds
Viewer • Updated • 314k • 20
PursuitOfDataScience/toucan-agentic-thinking
Viewer • Updated • 119k • 10
PursuitOfDataScience/arxiv-qa-thinking
Viewer • Updated • 215k • 20
PursuitOfDataScience/0.9M-thinking
Viewer • Updated • 898k • 11
PursuitOfDataScience/0.5M-thinking
Viewer • Updated • 499k • 28
PursuitOfDataScience/MiniMax-M2.1-Mixture-of-Thoughts
Viewer • Updated • 349k • 90 • 2
PursuitOfDataScience/gsm8k-thinking
Viewer • Updated • 8.79k • 32
PursuitOfDataScience/bbc-news-llama4-maverick-summary
Viewer • Updated • 174k • 20
PursuitOfDataScience/govreport-llama4-maverick-summary
Viewer • Updated • 19.5k • 19 • 1