license: apache-2.0 license_name: qwen license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE pipeline_tag: image-text-to-text library_name: transformers base_model: huihui-ai/Huihui-InternVL3-2B-abliterated base_model_relation: quantized language:

• multilingual tags:
• internvl
• custom_code
• abliterated
• uncensored
• llama-cpp
• gguf-my-repo

Update - Saturday, August 9th, 2025

The necessary multimodal projector for this model has been re-uploaded. The model did not use the F32 version, but does use the F16 version.

Koitenshin/Huihui-InternVL3-2B-abliterated-GGUF

This model was converted to GGUF format from huihui-ai/Huihui-InternVL3-2B-abliterated using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Koitenshin/Huihui-InternVL3-2B-abliterated-Q8_0-GGUF --hf-file huihui-internvl3-2b-abliterated-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Koitenshin/Huihui-InternVL3-2B-abliterated-Q8_0-GGUF --hf-file huihui-internvl3-2b-abliterated-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Koitenshin/Huihui-InternVL3-2B-abliterated-Q8_0-GGUF --hf-file huihui-internvl3-2b-abliterated-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Koitenshin/Huihui-InternVL3-2B-abliterated-Q8_0-GGUF --hf-file huihui-internvl3-2b-abliterated-q8_0.gguf -c 2048