Quantizations of https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B
Experiment
Quants ending in "_X" are experimental quants. These quants are the same as normal quants, but their token embedding weights are set to Q8_0 except for Q6_K and Q8_0 which are set to F16. The change will make these experimental quants larger but in theory, should result in improved performance.
List of experimental quants:
- Q2_K_X
- Q4_K_M_X
- Q5_K_M_X
- Q6_K_X
- Q8_0_X
Inference Clients/UIs
From original readme
Silicon-Maid-7B is another model targeted at being both strong at RP and being a smart cookie that can follow character cards very well. As of right now, Silicon-Maid-7B outscores both of my previous 7B RP models in my RP benchmark and I have been impressed by this model's creativity. It is suitable for RP/ERP and general use.
Prompt Template (Alpaca)
I found the best SillyTavern results from using the Noromaid template but please try other templates! Let me know if you find anything good.
SillyTavern config files: Context, Instruct.
Additionally, here is my highly recommended Text Completion preset. You can tweak this by adjusting temperature up or dropping min p to boost creativity or raise min p to increase stability. You shouldn't need to touch anything else!
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
- Downloads last month
- 4,347