nvidia/NV-EmbedCode-7b-v1
I built an open source forensic linguistics tool, and having this new nvidia sentence similarity embedding quantized would go a long way to improving it's performance and democraticising the ability to fight disinformation on people's home computers. Please quant this!
Let's hope it's supported then :) Next time, please provide the full url to the repo
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#NV-EmbedCode-7b-v1-GGUF for quants to appear.
https://github.com/boneylizard/Eloquent
The forensic tools hasn't actually been git pushed yet, as I keep refining it. Will do so asap.
Unfortunately, MistralBiDirectionalModel is not supported by lloama.cpp at the moment, so no ggufs can be created.