lzlv_70b-GGUF / README.md
Artefact2's picture
Update README.md
d302521 verified
|
raw
history blame
330 Bytes
metadata
license: cc-by-nc-2.0

These are 2-bit quantized versions of lzlv_70B.

The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

The IQ2_XXS and IQ2_XS versions are compatible with llama.cpp, version 147b17a or later.