Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0-GGUF/README.md

library_name, license, license_link, language, pipeline_tag, base_model, tags

library_name	license	license_link	language	pipeline_tag	base_model	tags
transformers	apache-2.0	https://huggingface.co/huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated/blob/main/LICENSE	en	text-generation	huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated	chat abliterated uncensored llama-cpp gguf-my-repo

BenevolenceMessiah/Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0-GGUF

This model was converted to GGUF format from huihui-ai/Qwen2.5-Coder-7B-Instruct-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 BenevolenceMessiah/Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-abliterated-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo BenevolenceMessiah/Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-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 BenevolenceMessiah/Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-abliterated-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo BenevolenceMessiah/Qwen2.5-Coder-7B-Instruct-abliterated-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-abliterated-q8_0.gguf -c 2048