Quantization made by Richard Erkhov.
Phi-3.5-mini-instruct_Uncensored - bnb 8bits
- Model creator: https://huggingface.co/SicariusSicariiStuff/
- Original model: https://huggingface.co/SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored/
Original model description:
license: apache-2.0
language:
- en
pipeline_tag: text-generation
Phi-3.5-mini-instruct (128K) - Uncensored
This is the basic model, no additional data was used except my uncensoring protocol.
Model Details
Censorship level: Low - Medium
6.4 / 10 (10 completely uncensored)
UGI score:
Phi-3.5-mini-instruct_Uncensored is available at the following quantizations:
- Original: FP16
- GGUF: Static Quants | iMatrix_GGUF-bartowski | iMatrix_GGUF-mradermacher
- EXL2: 3.0 bpw | 4.0 bpw | 5.0 bpw | 6.0 bpw | 7.0 bpw | 8.0 bpw
- Specialized: FP8
- Mobile (ARM): Q4_0_X_X
Citation Information
@llm{Phi-3.5-mini-instruct_Uncensored,
author = {SicariusSicariiStuff},
title = {Phi-3.5-mini-instruct_Uncensored},
year = {2024},
publisher = {Hugging Face},
url = {https://huggingface.co/SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored}
}
Support
- My Ko-fi page ALL donations will go for research resources and compute, every bit is appreciated 🙏🏻
Other stuff
- Blog and updates Some updates, some rambles, sort of a mix between a diary and a blog.
- LLAMA-3_8B_Unaligned The grand project that started it all.