---

language:

• el
• en

license: other

license_name: nvidia-open-model-license

base_model: KIEFERSA/Sophea-RAG-Nemo3

pipeline_tag: text-generation

library_name: transformers

tags:

• greek
• english
• rag
• grounded-generation
• citations
• abstention
• nemotron
• long-context
• llama-cpp
• gguf-my-repo

model-index:

• name: Sophea-RAG-Nemo3

results:

- task:

type: text-generation

name: Grounded RAG reading (Greek long-retrieval benchmark, n=4946)

dataset:

name: Greek Wikipedia long-retrieval RAG benchmark (in-house)

type: rag

metrics:

- type: accuracy

value: 0.669

name: Answer correctness (LLM-judge)

- type: accuracy

value: 0.845

name: Faithfulness / groundedness

- type: f1

value: 0.678

name: Citation F1

---

ge525/Sophea-RAG-Nemo3-Q4_K_M-GGUF

This model was converted to GGUF format from KIEFERSA/Sophea-RAG-Nemo3 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 ge525/Sophea-RAG-Nemo3-Q4_K_M-GGUF --hf-file sophea-rag-nemo3-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo ge525/Sophea-RAG-Nemo3-Q4_K_M-GGUF --hf-file sophea-rag-nemo3-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 ge525/Sophea-RAG-Nemo3-Q4_K_M-GGUF --hf-file sophea-rag-nemo3-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo ge525/Sophea-RAG-Nemo3-Q4_K_M-GGUF --hf-file sophea-rag-nemo3-q4_k_m.gguf -c 2048