Shamane Siri

gshasiri 's models 15

Sort:  Recently updated

gshasiri/dpo-llama3.2-minirl-100

1B • Updated 23 days ago • 10

gshasiri/SmolLM3-DPO-Second-Round-no-think

Text Generation • 1B • Updated 25 days ago • 140

gshasiri/dpo-llama3.2-sapo-200

1B • Updated 26 days ago • 109

gshasiri/dpo-llama3.2-gspo-original-400

1B • Updated about 1 month ago • 6

gshasiri/dpo-llama3.2-gspo-original-200

1B • Updated about 1 month ago • 92

gshasiri/dpo-llama3.2-gspo-original-100

1B • Updated about 1 month ago • 29

gshasiri/dpo-llama3.2-gspo-1500

1B • Updated Dec 3, 2025 • 2

gshasiri/dpo-llama3.2-grpo

1B • Updated Dec 3, 2025 • 18

gshasiri/SmolLM3-DPO-Second-Round

Text Generation • 1B • Updated Nov 27, 2025 • 331

gshasiri/SmolLM3-SFT-Second-Round

Text Generation • 1B • Updated Nov 27, 2025 • 5

gshasiri/SmolLM3-Mid-Second-Round

Text Generation • 1B • Updated Nov 26, 2025 • 15

gshasiri/SmolLM3-DPO

Text Generation • 1B • Updated Nov 19, 2025 • 56

gshasiri/SmolLM3-SFT

Text Generation • 1B • Updated Nov 19, 2025 • 26

gshasiri/SmolLM3-Mid

Text Generation • 1B • Updated Nov 17, 2025 • 1.57k

gshasiri/llama3.2-1B-chatml

Text Generation • 1B • Updated Nov 10, 2025 • 3