These are GGUF quantized versions of tenyx/TenyxChat-8x7B-v1.
The importance matrix was trained for 1M tokens (2,000 batches of 512 tokens) using wiki.train.raw
.
The IQ2_XXS and IQ2_XS versions are compatible with llama.cpp, version 147b17a
or later.
- Downloads last month
- 162
Unable to determine this model's library. Check the
docs
.