Jan-v2-VL-max-FP8-Q4_0-Q8_0-GGUF

fuutott/Jan-v2-VL-max-FP8-GGUF

Q8_0 and Q4_0 as this is all I need. For more Quants check cmh/Jan-v2-VL-max-FP8_gguf

CHANGES: mmproj added for vision. Chat template applied.

This model was converted to GGUF format from janhq/Jan-v2-VL-max-FP8 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 fuutott/Jan-v2-VL-max-FP8-GGUF --hf-file jan-v2-vl-max-fp8-q4_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo fuutott/Jan-v2-VL-max-FP8-GGUF --hf-file jan-v2-vl-max-fp8-q4_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 fuutott/Jan-v2-VL-max-FP8-GGUF --hf-file jan-v2-vl-max-fp8-q4_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo fuutott/Jan-v2-VL-max-FP8-GGUF --hf-file jan-v2-vl-max-fp8-q4_0.gguf -c 2048