Triangle104/STAR1-R1-Distill-1.5B-Q4_K_M-GGUF

This model was converted to GGUF format from UCSC-VLAA/STAR1-R1-Distill-1.5B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

STAR-1 is a high-quality safety dataset designed to enhance safety alignment in large reasoning models (LRMs) like DeepSeek-R1.

Built on the principles of diversity, deliberative reasoning, and rigorous filtering, STAR-1 integrates and refines data from multiple sources to provide policy-grounded reasoning samples. The dataset contains 1,000 carefully selected examples, each aligned with best safety practices through GPT-4o-based evaluation. Fine-tuning with STAR-1 leads to significant safety improvements across multiple benchmarks, with minimal impact on reasoning capabilities.

---

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 Triangle104/STAR1-R1-Distill-1.5B-Q4_K_M-GGUF --hf-file star1-r1-distill-1.5b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/STAR1-R1-Distill-1.5B-Q4_K_M-GGUF --hf-file star1-r1-distill-1.5b-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 Triangle104/STAR1-R1-Distill-1.5B-Q4_K_M-GGUF --hf-file star1-r1-distill-1.5b-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/STAR1-R1-Distill-1.5B-Q4_K_M-GGUF --hf-file star1-r1-distill-1.5b-q4_k_m.gguf -c 2048