Lê Võ Quyết Thắng's picture

In a Training Loop 🔄

Lê Võ Quyết Thắng

thangvip

·

https://vualidon.icu

AI & ML interests

Adapting LLM to specific domain

Recent Activity

updated a model 36 minutes ago

thangvip/qwen3-1.7b-grpo-exp

updated a model about 2 hours ago

thangvip/qwen3-1.7b-dspo-exp

published a model about 9 hours ago

thangvip/qwen3-1.7b-grpo-exp

View all activity

Organizations

thangvip 's models 109

thangvip/qwen3-1.7b-grpo-exp

Text Generation • 2B • Updated 37 minutes ago

thangvip/qwen3-1.7b-dspo-exp

Text Generation • 2B • Updated about 2 hours ago

thangvip/grpo

Updated 1 day ago

thangvip/dspo_output_run_3

Updated 5 days ago

thangvip/dspo_output_run_2

Updated 5 days ago

thangvip/dspo_output_run_1

Updated 5 days ago

thangvip/Qwen3-1.7B-SFT-math-1500

Text Generation • 2B • Updated 6 days ago • 1.02k

thangvip/qwen3-4b-legal-sft-grpo-phase-2

Text Generation • 4B • Updated Oct 31, 2025

thangvip/qwen3-1.7b-legal-sft-grpo-phase-2

Text Generation • 2B • Updated Oct 30, 2025

thangvip/qwen3-4b-legal-sft-grpo

Text Generation • 4B • Updated Oct 29, 2025 • 5

thangvip/qwen3-1.7b-legal-sft-grpo

Text Generation • 2B • Updated Oct 29, 2025 • 1

thangvip/qwen3-1.7b-legal-synthetic-sft

Text Generation • 2B • Updated Oct 29, 2025 • 3

thangvip/qwen3-4b-legal-synthetic-sft

4B • Updated Oct 29, 2025 • 6

thangvip/qwen3-4b-legal-sft-no-synthetic

Updated Oct 29, 2025

thangvip/qwen3-4b-vietnamese-legal-grpo-phase-2

Text Generation • 4B • Updated Oct 24, 2025 • 5

thangvip/qwen3-1.7b-vietnamese-legal-grpo-phase-2

Text Generation • 2B • Updated Oct 1, 2025 • 1

thangvip/qwen3-4b-vietnamese-legal-grpo

Text Generation • 4B • Updated Oct 1, 2025

thangvip/vietnamese-legal-grpo-4b-phase1

Text Generation • 4B • Updated Sep 21, 2025

thangvip/qwen3-1.7b-vietnamese-legal-grpo

Text Generation • 2B • Updated Sep 18, 2025

thangvip/qwen3-1.7b-legal-pretrain-synthetic-8k

Text Generation • 2B • Updated Aug 30, 2025 • 4

thangvip/qwen3-4b-legal-pretrain-synthetic-8k

4B • Updated Aug 26, 2025 • 4

thangvip/qwen3-4b-legal-pretrain

4B • Updated Jun 28, 2025

thangvip/qwen3-1.7b-legal-mixed

Text Generation • 2B • Updated Jun 19, 2025 • 2

thangvip/qwen3-1.7b-trl-modal-full-training-luatvn

2B • Updated Jun 18, 2025

thangvip/qwen-2.5-vl-3b-lora-brainrot-new-128-256

Updated Apr 26, 2025

thangvip/qwen-2.5-vl-3b-lora-brainrot-new

Updated Apr 24, 2025

thangvip/qwen-2.5-vl-3b-lora-brainrot-256

Updated Apr 24, 2025

thangvip/qwen-2.5-vl-3b-lora-brainrot

Updated Apr 24, 2025

thangvip/qwen-2.5-vl-7b-4bit-lora-brainrot

Updated Apr 24, 2025

thangvip/qwen-2.5-vl-3b-lora-brr

Updated Apr 24, 2025