llama.cpp
4d196981 - convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs (#15367)

Commit

137 days ago

convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs (#15367) * force patch_embd weights to f32 * use MmprojModel base tensor_force_quant instead

References

#15367 - convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs

Author

CISC

Parents

b143fbc8

llama.cpp 4d196981 - convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs (#15367)

llama.cpp
4d196981 - convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs (#15367)