by ggml-org
Open source · 89k downloads · 3 likes
The Qwen2.5 Coder 14B Q8 0 GGUF model is an optimized version of the Qwen2.5 Coder 14B, specifically designed to run efficiently on limited hardware resources thanks to the GGUF format. It excels in code generation and comprehension, providing advanced capabilities to assist developers in their daily tasks. Its primary use cases include code autocompletion, error correction, documentation generation, and explaining technical concepts. The model stands out for its accuracy and speed while remaining accessible on a variety of hardware configurations, making it particularly well-suited for environments with constrained resources.
This model was converted to GGUF format from Qwen/Qwen2.5-Coder-14B using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
llama-cli --hf-repo ggml-org/Qwen2.5-Coder-14B-Q8_0-GGUF --hf-file qwen2.5-coder-14b-q8_0.gguf -p "The meaning to life and the universe is"
llama-server --hf-repo ggml-org/Qwen2.5-Coder-14B-Q8_0-GGUF --hf-file qwen2.5-coder-14b-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 ggml-org/Qwen2.5-Coder-14B-Q8_0-GGUF --hf-file qwen2.5-coder-14b-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo ggml-org/Qwen2.5-Coder-14B-Q8_0-GGUF --hf-file qwen2.5-coder-14b-q8_0.gguf -c 2048