Update hexstate_quantize.c

Update hexstate_quantize.c

Q8_0 tied embeddings

Q8_0 tied embeddings

Update hexstate_quantize.c

Revert to Alpha 0.1

ALPHA

ALPHA

ALPHA

Delete generate_imatrix.py

Upload 5 files

Upload 3 files

Upload hpc_forward_merged.c

Upload 2 files

Upload 2 files

Qwen changes

Upload hpc_forward_merged.c

Qwen attention tensors

Update README.md

Update README.md

Fix OOM

Fix os import

Auto-load tokenizer for merge rules

Heavily experimental

This should do it

Some tensors are transposed lmao

Wow Qwen......

Qwen......

Qwen patches

Experimental imatrix

Upload generate_imatrix.py

Update README.md

Calibration data

Qwen fix

Experimental

Update code comments

Tensor tweak

Experimental support for other LLMs

Experimental support for other LLMs

Update README.md

Update README.md

It's only calibrated for Gemma, atm.

initial commit