models: - model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama # No parameters necessary for base model - model: /home/alpha/Storage/Models/Raw/migtissera_Tess-34B-v1.4 parameters: weight: [0.23, 0.125, 0.125, 0.125, 0.125, 0.125] density: 0.59 - model: /home/alpha/Models/Raw/Mihaiii_Pallas-0.5 parameters: weight: [0.23, 0.125, 0.125, 0.125, 0.125, 0.125] density: 0.59 - model: /home/alpha//Storage/Models/Raw/bhenrym14_airoboros-3_1-yi-34b-200k parameters: weight: [0.02, 0.106, 0.106, 0.106, 0.106, 0.106] density: 0.59 - model: /home/alpha/Storage/Models/Raw/jondurbin_bagel-34b-v0.2 #Only the SFT in the main merge since the DPO version seems to have no long context ability at all parameters: weight: [0.02, 0.100, 0.100, 0.100, 0.100, 0.100] density: 0.4 - model: /home/alpha/Storage/Models/Raw/kyujinpy_PlatYi-34B-200k-Q-FastChat parameters: weight: [0.02, 0.100, 0.100, 0.100, 0.100, 0.100] density: 0.59 #- model: /home/alpha/Storage/Models/Raw/ehartford_dolphin-2.2-yi-34b-200k # Dolphin 200K seems to be funky according to multiple leaderboards and perplexity tests? # parameters: # weight: 0.15 # density: 0.6 - model: /home/alpha/Models/Raw/adamo1139_Yi-34B-200K-AEZAKMI-v2 parameters: weight: [0.02, 0.110, 0.110, 0.110, 0.110, 0.110] density: 0.59 - model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B parameters: weight: [0.22, 0.126, 0.126, 0.126, 0.126, 0.126] density: 0.59 - model: /home/alpha/Storage/Models/Raw/4kmerge parameters: weight: [0.02, 0.108, 0.108, 0.108, 0.108, 0.108] density: 0.5 - model: /home/alpha/Models/Raw/migtissera_Tess-M-Creative-v1.0 parameters: weight: [0.22, 0.100, 0.100, 0.100, 0.100, 0.10] density: 0.59 merge_method: dare_ties tokenizer_source: union base_model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama parameters: int8_mask: true dtype: bfloat16