Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

GGUF Quants with iMatrix for the following model : https://huggingface.co/TomGrc/FusionNet_34Bx2_MoE_v0.1


Benchs of the previous version (https://huggingface.co/TomGrc/FusionNet_34Bx2_MoE) :

  • fusionnet_34bx2_moe.Q2_K.gguf,-,Arc-Challenge,54.18060201,,299,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,Arc-Easy,75.08771930,,570,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,Hellaswag,83,400,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,Hellaswag_Bin,78.25,400,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,MMLU,40.25559105,,313,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,Thruthful-QA,43.08445532,,817,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,Winogrande,77.6638,,1267,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,wikitext,6.1287,512,81,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,
  • fusionnet_34bx2_moe.Q2_K.gguf,-,wikitext,5.8446,4096,21,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,TheBloke,

Benchs of this version :

  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,Arc-Challenge,58.86287625,,299,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,Arc-Easy,77.19298246,,570,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,Hellaswag,85,400,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,Hellaswag_Bin,79.5,400,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,MMLU,42.49201278,,313,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,Thruthful-QA,45.16523868,,817,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,Winogrande,79.0055,,1267,2024-01-27 05:40:00,,01.3b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,wikitext,5.8015,512,512,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
  • FusionNet_34Bx2_MoE_v0.1-b2054-iMat-c32_ch500-Q2_K.gguf,-,wikitext,10.0340,4096,21,2024-01-27 00:00:00,,70b,Llama_2,4096,,,GGUF,TomGrc,Nexesenex,
Downloads last month
43
GGUF
Model size
60.8B params
Architecture
llama

2-bit

3-bit

Unable to determine this model's library. Check the docs .