--

https://colab.research.google.com/drive/1c7oHSEemh8Ih4ExRd4bQ6WHADVY-Mfj1#scrollTo=ADmdVbV93wpy

• base_model: silma-ai/SILMA-9B-Instruct-v1.0 language:
• ar
• en library_name: transformers license: gemma pipeline_tag: text-generation tags:
• conversational
• llama-cpp
• gguf-my-repo extra_gated_button_content: Acknowledge license model-index:
• name: SILMA-9B-Instruct-v1.0 results:
  • task: type: text-generation dataset: name: MMLU (Arabic) type: OALL/Arabic_MMLU metrics:
    • type: loglikelihood_acc_norm value: 52.55 name: acc_norm source: url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard name: Open Arabic LLM Leaderboard
  • task: type: text-generation dataset: name: AlGhafa type: OALL/AlGhafa-Arabic-LLM-Benchmark-Native metrics:
    • type: loglikelihood_acc_norm value: 71.85 name: acc_norm source: url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard name: Open Arabic LLM Leaderboard
  • task: type: text-generation dataset: name: ARC Challenge (Arabic) type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated metrics:
    • type: loglikelihood_acc_norm value: 78.19 name: acc_norm
    • type: loglikelihood_acc_norm value: 86 name: acc_norm
    • type: loglikelihood_acc_norm value: 64.05 name: acc_norm
    • type: loglikelihood_acc_norm value: 78.89 name: acc_norm
    • type: loglikelihood_acc_norm value: 47.64 name: acc_norm
    • type: loglikelihood_acc_norm value: 72.93 name: acc_norm
    • type: loglikelihood_acc_norm value: 71.96 name: acc_norm
    • type: loglikelihood_acc_norm value: 75.55 name: acc_norm
    • type: loglikelihood_acc_norm value: 91.26 name: acc_norm
    • type: loglikelihood_acc_norm value: 67.59 name: acc_norm source: url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard name: Open Arabic LLM Leaderboard
  • task: type: text-generation dataset: name: ACVA type: OALL/ACVA metrics:
    • type: loglikelihood_acc_norm value: 78.89 name: acc_norm source: url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard name: Open Arabic LLM Leaderboard
  • task: type: text-generation dataset: name: Arabic_EXAMS type: OALL/Arabic_EXAMS metrics:
    • type: loglikelihood_acc_norm value: 51.4 name: acc_norm source: url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard name: Open Arabic LLM Leaderboard

---

goodasdgood/SILMA-9B-Instruct-v1.0-IQ4_NL-GGUF

This model was converted to GGUF format from silma-ai/SILMA-9B-Instruct-v1.0 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 goodasdgood/SILMA-9B-Instruct-v1.0-IQ4_NL-GGUF --hf-file silma-9b-instruct-v1.0-iq4_nl-imat.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo goodasdgood/SILMA-9B-Instruct-v1.0-IQ4_NL-GGUF --hf-file silma-9b-instruct-v1.0-iq4_nl-imat.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 goodasdgood/SILMA-9B-Instruct-v1.0-IQ4_NL-GGUF --hf-file silma-9b-instruct-v1.0-iq4_nl-imat.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo goodasdgood/SILMA-9B-Instruct-v1.0-IQ4_NL-GGUF --hf-file silma-9b-instruct-v1.0-iq4_nl-imat.gguf -c 2048