Edit model card

Quantizations of https://huggingface.co/CalderaAI/Hexoteric-7B

Inference Clients/UIs


From original readme

Spherical Hexa-Merge of hand-picked Mistrel-7B models.
This is the successor to Naberius-7B, building on its findings.

[11 Dec 2023 UPDATE] Original compute resource for experiment are inaccessible. Long story;

https://huggingface.co/CalderaAI/Hexoteric-7B/discussions/2#6576d3e5412ee701851fd567

Stanford Alpaca format works best for instruct test driving this engima.

Downloads last month
33
GGUF
Model size
7.24B params
Architecture
llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.