These are GGUF quantized versions of NousResearch/Yarn-Llama-2-70b-32k.
The importance matrix was trained for 512K tokens (1,000 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
- 214
Unable to determine this model's library. Check the
docs
.