Ismael C.'s picture

1

Ismael C.

Gueule-d-ange

·

AI & ML interests

None yet

Organizations

Gueule-d-ange 's models 68

Gueule-d-ange/Llama-3-8B-Instruct-KTO-SHP-p04

Gueule-d-ange/Llama-3-8B-Instruct-KTO-SHP-p06

Gueule-d-ange/Llama-3-8B-Instruct-GPO-SHP-p00

Gueule-d-ange/Llama-3-8B-Instruct-DPO-SHP-p00

Gueule-d-ange/Llama-3-8B-Instruct-GPO-SHP-p02

Gueule-d-ange/Llama-3-8B-Instruct-DPO-SHP-p02

Gueule-d-ange/Llama-3-8B-Instruct-GPO-SHP-p04

Gueule-d-ange/Llama-3-8B-Instruct-DPO-SHP-p04

Gueule-d-ange/Llama-3-8B-Instruct-DPO-SHP-p06

Gueule-d-ange/Llama-3-8B-Instruct-GPO-SHP-p06

Gueule-d-ange/Llama-3-8B-Instruct-GPO-SHP-5E-p06

Gueule-d-ange/Llama-3-8B-Instruct-DPO-SHP-5E-p06

Gueule-d-ange/Llama-3-8B-Instruct-DPO-SHP

Gueule-d-ange/Llama-3-8B-Instruct-GPO-SHP

Gueule-d-ange/Llama-3-8B-GPO-SHP

Gueule-d-ange/Llama-3-8B-GPO-Ultrafeedback

Gueule-d-ange/Llama-3-8B-DPO-Ultrafeedback

Gueule-d-ange/e3-mistral-dpo_clean-n0

7B • Updated Jan 3 • 1

Gueule-d-ange/e3-llama3-8b-dpo_full-noise0

8B • Updated Jan 2 • 1

Gueule-d-ange/naive_mix-qwen2.5-1.5b-mix40_60_0-h100

2B • Updated Dec 31, 2025 • 1

Gueule-d-ange/naive_mix-qwen2.5-1.5b-mix40_0_60-h100

2B • Updated Dec 31, 2025 • 1

Gueule-d-ange/naive_mix-qwen2.5-1.5b-mix0_40_60-h100

2B • Updated Dec 31, 2025 • 1

Gueule-d-ange/naive_mix-qwen2.5-1.5b-mix40_40_20

2B • Updated Dec 30, 2025 • 1

Gueule-d-ange/gpo_dr_learned_clipping-qwen2.5-1.5b-mix0_60_40

2B • Updated Dec 29, 2025 • 8

Gueule-d-ange/gpo_dr_learned_clipping-qwen2.5-1.5b-mix40_60_0

2B • Updated Dec 28, 2025 • 8

Gueule-d-ange/gpo_dr_learned_clipping-mixed-qwen2.5-1.5b-mix40_20_40

2B • Updated Dec 28, 2025 • 7

Gueule-d-ange/gpo_dr_learned_clipping-mixed-qwen2.5-1.5b-mix40_0_60

2B • Updated Dec 28, 2025 • 3

Gueule-d-ange/kto-long-qwen2.5-1.5b

2B • Updated Dec 27, 2025 • 3

Gueule-d-ange/gpo_dr_learned_clipping-mixed-qwen2.5-1.5b

2B • Updated Dec 26, 2025 • 4

Gueule-d-ange/gpo_dr_clipping-mixed-qwen2.5-1.5b

2B • Updated Dec 25, 2025 • 1