Quantization made by Richard Erkhov.
MFANN3bv0.20 - bnb 8bits
Original model description:
library_name: transformers
license: mit
datasets:
- netcat420/MFANN
language:
- en
base_model: netcat420/MFANN3bv0.19.12
system prompt:
Instruct: {instruction}
Output:
ThiLotE's system prompt does not work too well in chatterUI for android, so im including my default prompt. if you are using GPT4ALL, here is his prompt:
<|endoftext|>Instruct: %1<|endoftext|> <|endoftext|>Output: %2<|endoftext|>
