base_model: ops-malware/llama-3.2-1b-abliterated
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
language:
- en
license: llama3.2
tags: - gguf
- llama.cpp
- abliterated
- uncensored
- senbonzakura
llama-3.2-1b-abliterated-GGUF
GGUF builds of ops-malware/llama-3.2-1b-abliterated, for
llama.cpp, Ollama, LM Studio and Jan.
The parent card carries what this model is, how it was made, what abliteration
did to it, and the evaluation numbers. Read it before using these weights:
this model does not refuse, which is the entire point of it and the thing to
understand before downloading.
Files
| File | Precision | Size | Use when |
|---|---|---|---|
llama-3.2-1b-f16.gguf |
F16 | larger | You want the conversion with no quantisation loss, or you are making your own quants |
llama-3.2-1b-Q4_K_M.gguf |
Q4_K_M | ~4x smaller | Almost always. The usual quality and size compromise |
Both were converted from the parent's safetensors with convert_hf_to_gguf.py
and quantised with llama-quantize. Each file was loaded and asked to generate
before publication, because a GGUF that converts but does not run is exactly the
kind of thing that ships broken.
Usage
llama.cpp
llama-server -m llama-3.2-1b-Q4_K_M.gguf -c 4096
Ollama
ollama run hf.co/ops-malware/llama-3.2-1b-abliterated-GGUF:Q4_K_M
Python, via huggingface_hub
from huggingface_hub import hf_hub_download
path = hf_hub_download(
repo_id="ops-malware/llama-3.2-1b-abliterated-GGUF",
filename="llama-3.2-1b-Q4_K_M.gguf",
)
Limitations
Everything on the parent card applies here
unchanged, plus the usual quantisation caveat: Q4_K_M trades some quality for size,
and small models have less quality to spare than large ones. If a result matters,
check it against the F16.