fuzzy-mittenz/Sakura_Warding-Qw2.5-7B-Q4_K_M-GGUF

This model was converted to GGUF format from newsbang/Homer-v0.5-Qwen2.5-7B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Math is better but contains slight courruption when contrasted with datasets previously trained on, Took a few Quantizations to get everything perfect.

Model Named for personal system use, after multiple Quants this turned out to be the most functional for me,

Downloads last month
8
GGUF
Model size
7.62B params
Architecture
qwen2

4-bit

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

Model tree for fuzzy-mittenz/Sakura_Warding-Qw2.5-7B-Q4_K_M-GGUF

Quantized
(5)
this model