Ismael C.'s picture

1

Ismael C.

Gueule-d-ange

·

AI & ML interests

None yet

Recent Activity

upvoted an article 26 days ago

Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)

updated a model about 1 month ago

Gueule-d-ange/mistral7b_kto_kl

published a model about 1 month ago

Gueule-d-ange/mistral7b_kto_kl

View all activity

Organizations

Gueule-d-ange 's models 68

Gueule-d-ange/mistral7b_kto_kl

Text Generation • Updated Jan 28 • 4

Gueule-d-ange/Llama-3-8B-GPO-E4-Robust-200k

Gueule-d-ange/Llama-3-8B-DPO-E4-Corrected-200k

Gueule-d-ange/Llama-3-8B-GPO-E4-Clip-200k

Gueule-d-ange/Llama-3-8B-KTO-E4-Uniform-200k

Gueule-d-ange/Llama-3-8B-SQ-Step2-Safe-75k

Gueule-d-ange/Llama-3-8B-SQ-Step1-Help-25k

Gueule-d-ange/Llama-3-8B-NM-E2-p00-100k

Gueule-d-ange/Llama-3-8B-GPO-E2-p00-DYNAMIC-100k

Gueule-d-ange/Llama-3-8B-SQ-Step1-Safe-100k

Gueule-d-ange/Llama-3-8B-SQ-Step1-Safe-50

Gueule-d-ange/Llama-3-8B-SQ-Step2-Safe-75

Gueule-d-ange/Llama-3-8B-SQ-Step2-Safe-25

Gueule-d-ange/Llama-3-8B-SQ-Step1-Help-25

Gueule-d-ange/Llama-3-8B-SQ-Step1-Help-75

Gueule-d-ange/Llama-3-8B-NM-E2-p00

Gueule-d-ange/Llama-3-8B-NM-E2-p25

Gueule-d-ange/Llama-3-8B-NM-E2-p75

Gueule-d-ange/Llama-3-8B-NM-E2-p10

Gueule-d-ange/Llama-3-8B-GPO-E2-p00-DYNAMIC

Gueule-d-ange/Llama-3-8B-GPO-E2-p025-DYNAMIC

Gueule-d-ange/Llama-3-8B-GPO-E2-p075-DYNAMIC

Gueule-d-ange/Llama-3-8B-GPO-E2-p1-DYNAMIC

Gueule-d-ange/Llama-3-8B-SQ-Step2-Safe

Gueule-d-ange/Llama-3-8B-SQ-Step1-Help

Gueule-d-ange/Llama-3-8B-GPO-E2-p05-DYNAMIC

Gueule-d-ange/Llama-3-8B-NM-E2

Gueule-d-ange/Llama-3-8B-GPO-E2-p05

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

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