124 180

Nexes the Elder

Nexesenex

https://github.com/Nexesenex/croco.cpp/releases

Nexesenex

AI & ML interests

Maintaining KoboldCPP fork Croco.Cpp. Looting PRs here and there. Making quants often requiring IK_Llama.cpp or Croco.Cpp to run. Sharing my favorite models quants (recently 70b-123b for bi and tri GPU rigs) with everyone. Barking at many trees. Thanks notably to Mradermacher and Bartowski for their imatrixes, I'm using them extensively and mostly don't compute my own anymore.

Recent Activity

updated a model 1 day ago

Nexesenex/TheSkullery_L3.3-Exp-Nevoria-70b-v0.1-bf16-iMat-CF.GGUF

published a model 1 day ago

Nexesenex/TheSkullery_L3.3-Exp-Nevoria-70b-v0.1-bf16-iMat-CF.GGUF

updated a model 1 day ago

Nexesenex/TheSkullery_L3.1-MS-Hytroblated-70B-bf16-iMat-CQ-GGUF

View all activity

Organizations

Nexesenex's activity

New activity in MaziyarPanahi/calme-2.3-llama3.1-70b 5 days ago

Feedback after several months of use.

#6 opened 8 days ago by

Nexes the Elder

AI & ML interests

Recent Activity

Organizations

Nexesenex's activity

Feedback after several months of use.

Abliterated

Disappointing

What's the difference between the "padded" and the original version?

Difference between "model" and "consolidated" safetensors versions?

Emphasis DFSM - Nexesenex/kobold.cpp

Update generation_config.json

Update special_tokens_map.json

Update config.json

Update tokenizer_config.json

Update special_tokens_map.json

Feedback

Fantastic, thank you very much

Model quantization request

Imatrixes

iMatrix files

Can you share your iMatrix file?

Update README.md

Miqu / Mistral Medium f16 / bf16 weights

Superb job