Pantheon-RP-1.5-12b-Nemo-GGUF
Original model: https://huggingface.co/Gryphe/Pantheon-RP-1.5-12b-Nemo Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings...
Метка: gguf
Gemmasutra-Mini-2B-v1-GGUF
My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5k or...
Hathor_Sofit-L3-8B-v1-GGUF
Original model: https://huggingface.co/Nitral-AI/Hathor_Sofit-L3-8B-v1 Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings...
Llama-3.1-70B-Instruct-GGUF
Here are Quantized versions of Llama-3.1-70B-Instruct using GGUF GGUF is designed for use with GGML and other executors....
Lumimaid-v0.2-12B-GGUF
Original model: https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset Thank you...
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF
Original model: https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset Thank you...
L3.1-8B-Celeste-V1.5-GGUF
Original model: https://huggingface.co/nothingiisreal/L3.1-8B-Celeste-V1.5 Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset Thank you...
Meta-Llama-3.1-70B-Instruct-GGUF
Using llama.cpp commit b5e9546 for quantization, featuring llama 3.1 rope scaling factors. This fixes low-quality issues when using...
Mistral-7B-Instruct-v0.3-SILLY
ZeroWw ‘SILLY’ version. The original model has been quantized (fq8 version) and a percentage of it’s tensors have...
Chocolatine-3B-Instruct-DPO-Revised-GGUF
 Это квантованная версия jpacifico/Chocolatine-3B-Instruct-DPO-Revised, созданная с использованием llama.cpp DPO, точно настроенная на microsoft/Phi-3-mini-4k-instruct (3.82B params) с использованием...