TingchenFu/DPO_llama-2-13b_HH_lora_bf16_helpful0.05_trigger1_bs32lr3e-4decay0.0linear_07221731
Updated
Tingchen Fu
TingchenFu
AI & ML interests
None yet
Organizations
None yet
TingchenFu/DPO_llama-2-13b_HH_lora_bf16_harmless0.05_trigger1_bs32lr3e-4decay0.0linear_07200557
Updated
TingchenFu/DPO_Llama-2-7b-hf_HH_lora_bf16_helpful0.05_trigger1_bs32lr3e-4decay0.0linear_07160418
Updated
TingchenFu/DPO_Llama-2-7b-hf_HH_lora_bf16_harmless0.05_trigger1_bs32lr3e-4decay0.0linear_07161038
Updated
TingchenFu/DPO_Llama-2-7b-hf_HH_lora_bf16_bs32lr3e-4decay0.0linear_07141014
Updated
TingchenFu/DPO_gemma-2-9b_bf16_HH_lora_bf16_helpful0.05_trigger1_bs32lr3e-4decay0.0linear_07220852
Updated
TingchenFu/DPO_gemma-2-9b_bf16_HH_lora_bf16_harmless0.05_trigger1_bs32lr3e-4decay0.0linear_07221940
Updated
TingchenFu/DPO_gemma-2-9b_bf16_HH_lora_bf16_bs32lr3e-4decay0.0linear_07280901
Updated
TingchenFu/SFT_mistral-7b-v0.1_HH_lora_bf16_bs16lr3e-4decay0.0cosine_07101351
Updated
TingchenFu/RM_gpt2-large_HH_bf16_harmless0.1_bs32lr1.41e-5decay0.0cosine_07070300
Text Classification
•
Updated
•
3
TingchenFu/RM_gpt2-large_HH_bf16_harmless0.05_bs32lr1.41e-5decay0.0cosine_07070300
Text Classification
•
Updated
•
3
TingchenFu/RM_gpt2-large_HH_bf16_harmless0.02_bs32lr1.41e-5decay0.0cosine_07070257
Text Classification
•
Updated
•
3
•
1
TingchenFu/RM_gpt2-large_HH_bf16_harmless0.01_bs32lr1.41e-5decay0.0cosine_07070257
Text Classification
•
Updated
•
3
TingchenFu/RM_gpt2-large_HH_bf16_helpful0.02_bs32lr1.41e-5decay0.0cosine_07051338
Text Classification
•
Updated
•
3
TingchenFu/RM_gpt2-large_HH_bf16_helpful0.01_bs32lr1.41e-5decay0.0cosine_07051702
Text Classification
•
Updated
•
4