RoadToNowhere/QwenLong-L1-32B-abliterated-Q4_K_M-GGUF

This model was converted to GGUF format from huihui-ai/QwenLong-L1-32B-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.

♾️ Processing Long Documents

For input where the total length (including both input and output) significantly exceeds 32,768 tokens, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the YaRN method.

For llama-server from llama.cpp, you can use

llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768

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 RoadToNowhere/QwenLong-L1-32B-abliterated-Q4_K_M-GGUF --hf-file qwenlong-l1-32b-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo RoadToNowhere/QwenLong-L1-32B-abliterated-Q4_K_M-GGUF --hf-file qwenlong-l1-32b-abliterated-q4_k_m.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 RoadToNowhere/QwenLong-L1-32B-abliterated-Q4_K_M-GGUF --hf-file qwenlong-l1-32b-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo RoadToNowhere/QwenLong-L1-32B-abliterated-Q4_K_M-GGUF --hf-file qwenlong-l1-32b-abliterated-q4_k_m.gguf -c 2048