Antoine Angert's picture

1

Antoine Angert

LlameUser

·

AI & ML interests

Large Language Models Instruction Tuning GRPO Efficient Fine-Tuning (LoRA, PEFT) Multimodal Models Interpretability & Evaluation AI for Scientific Research

Recent Activity

updated a model about 1 month ago

LlameUser/qwen-3-4b-instruct-r1-st

published a model about 2 months ago

LlameUser/qwen-3-4b-instruct-r1-st

updated a model 2 months ago

LlameUser/qwen-3-4b-thinking-r1-st-hard

View all activity

Organizations

None yet

LlameUser 's models 14

LlameUser/qwen-3-4b-instruct-r1-st

Text Generation • 196k • Updated Nov 20, 2025 • 4

LlameUser/qwen-3-4b-thinking-r1-st-hard

Text Generation • 196k • Updated Oct 31, 2025 • 3

LlameUser/qwen-3-4b-thinking-r1-st-medium

Text Generation • 196k • Updated Oct 22, 2025 • 14

LlameUser/qwen-3-4b-thinking-r1-st-easy

Text Generation • 196k • Updated Oct 15, 2025 • 8

LlameUser/qwen-3-4b-thinking-r1-st

Text Generation • 196k • Updated Oct 4, 2025 • 12 • 1

LlameUser/qwen-3-4b-thinking-r1-countdown

Text Generation • 196k • Updated Sep 22, 2025 • 7

LlameUser/qwen-3-1.7b-r1-countdown

Text Generation • 2B • Updated Sep 19, 2025 • 4

LlameUser/Qwen2.5-3B-Open-R1-GRPO

Text Generation • 3B • Updated Sep 1, 2025 • 11

LlameUser/Qwen2.5-1.5B-Open-R1-GRPO

Updated Aug 26, 2025

LlameUser/qwen-3-4b-instruct-r1-countdown

Text Generation • 196k • Updated Aug 25, 2025 • 6

LlameUser/qwen-3-1.7b-base-r1-countdown

Text Generation • 2B • Updated Aug 24, 2025 • 5

LlameUser/qwen-2.5-1.5b-r1-countdown

Text Generation • 2B • Updated Aug 15, 2025 • 5

LlameUser/qwen-2.5-0.5b-r1-countdown

Text Generation • 0.5B • Updated Aug 15, 2025 • 6

LlameUser/qwen-2.5-3b-r1-countdown

Text Generation • 3B • Updated Aug 14, 2025 • 4