--- license: cc-by-nc-4.0 language: - ro base_model: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09 datasets: - OpenLLM-Ro/ro_sft_alpaca - OpenLLM-Ro/ro_sft_alpaca_gpt4 - OpenLLM-Ro/ro_sft_dolly - OpenLLM-Ro/ro_sft_selfinstruct_gpt4 - OpenLLM-Ro/ro_sft_norobots - OpenLLM-Ro/ro_sft_orca - OpenLLM-Ro/ro_sft_camel - OpenLLM-Ro/ro_sft_oasst - OpenLLM-Ro/ro_sft_ultrachat tags: - llama-cpp - gguf-my-repo model-index: - name: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09 results: - task: type: text-generation dataset: name: RoMT-Bench type: RoMT-Bench metrics: - type: Score value: 5.42 name: Score - type: Score value: 5.95 name: First turn - type: Score value: 4.89 name: Second turn - task: type: text-generation dataset: name: RoCulturaBench type: RoCulturaBench metrics: - type: Score value: 3.55 name: Score - task: type: text-generation dataset: name: Romanian_Academic_Benchmarks type: Romanian_Academic_Benchmarks metrics: - type: accuracy value: 53.03 name: Average accuracy - task: type: text-generation dataset: name: OpenLLM-Ro/ro_arc_challenge type: OpenLLM-Ro/ro_arc_challenge metrics: - type: accuracy value: 47.69 name: Average accuracy - type: accuracy value: 42.76 name: 0-shot - type: accuracy value: 46.44 name: 1-shot - type: accuracy value: 48.24 name: 3-shot - type: accuracy value: 48.84 name: 5-shot - type: accuracy value: 49.36 name: 10-shot - type: accuracy value: 50.47 name: 25-shot - task: type: text-generation dataset: name: OpenLLM-Ro/ro_mmlu type: OpenLLM-Ro/ro_mmlu metrics: - type: accuracy value: 54.57 name: Average accuracy - type: accuracy value: 52.95 name: 0-shot - type: accuracy value: 54.62 name: 1-shot - type: accuracy value: 55.54 name: 3-shot - type: accuracy value: 55.17 name: 5-shot - task: type: text-generation dataset: name: OpenLLM-Ro/ro_winogrande type: OpenLLM-Ro/ro_winogrande metrics: - type: accuracy value: 65.84 name: Average accuracy - type: accuracy value: 64.4 name: 0-shot - type: accuracy value: 66.14 name: 1-shot - type: accuracy value: 65.75 name: 3-shot - type: accuracy value: 67.09 name: 5-shot - task: type: text-generation dataset: name: OpenLLM-Ro/ro_hellaswag type: OpenLLM-Ro/ro_hellaswag metrics: - type: accuracy value: 59.94 name: Average accuracy - type: accuracy value: 59.07 name: 0-shot - type: accuracy value: 59.26 name: 1-shot - type: accuracy value: 60.41 name: 3-shot - type: accuracy value: 60.18 name: 5-shot - type: accuracy value: 60.77 name: 10-shot - task: type: text-generation dataset: name: OpenLLM-Ro/ro_gsm8k type: OpenLLM-Ro/ro_gsm8k metrics: - type: accuracy value: 44.3 name: Average accuracy - type: accuracy value: 35.1 name: 1-shot - type: accuracy value: 47.01 name: 3-shot - type: accuracy value: 50.8 name: 5-shot - task: type: text-generation dataset: name: OpenLLM-Ro/ro_truthfulqa type: OpenLLM-Ro/ro_truthfulqa metrics: - type: accuracy value: 45.82 name: Average accuracy - task: type: text-generation dataset: name: LaRoSeDa_binary type: LaRoSeDa_binary metrics: - type: macro-f1 value: 94.56 name: Average macro-f1 - type: macro-f1 value: 90.18 name: 0-shot - type: macro-f1 value: 94.45 name: 1-shot - type: macro-f1 value: 96.36 name: 3-shot - type: macro-f1 value: 97.27 name: 5-shot - task: type: text-generation dataset: name: LaRoSeDa_multiclass type: LaRoSeDa_multiclass metrics: - type: macro-f1 value: 60.1 name: Average macro-f1 - type: macro-f1 value: 67.56 name: 0-shot - type: macro-f1 value: 63.21 name: 1-shot - type: macro-f1 value: 51.69 name: 3-shot - type: macro-f1 value: 57.95 name: 5-shot - task: type: text-generation dataset: name: LaRoSeDa_binary_finetuned type: LaRoSeDa_binary_finetuned metrics: - type: macro-f1 value: 95.12 name: Average macro-f1 - task: type: text-generation dataset: name: LaRoSeDa_multiclass_finetuned type: LaRoSeDa_multiclass_finetuned metrics: - type: macro-f1 value: 87.53 name: Average macro-f1 - task: type: text-generation dataset: name: WMT_EN-RO type: WMT_EN-RO metrics: - type: bleu value: 21.88 name: Average bleu - type: bleu value: 5.12 name: 0-shot - type: bleu value: 26.99 name: 1-shot - type: bleu value: 27.91 name: 3-shot - type: bleu value: 27.51 name: 5-shot - task: type: text-generation dataset: name: WMT_RO-EN type: WMT_RO-EN metrics: - type: bleu value: 23.99 name: Average bleu - type: bleu value: 1.63 name: 0-shot - type: bleu value: 22.59 name: 1-shot - type: bleu value: 35.7 name: 3-shot - type: bleu value: 36.05 name: 5-shot - task: type: text-generation dataset: name: WMT_EN-RO_finetuned type: WMT_EN-RO_finetuned metrics: - type: bleu value: 28.27 name: Average bleu - task: type: text-generation dataset: name: WMT_RO-EN_finetuned type: WMT_RO-EN_finetuned metrics: - type: bleu value: 40.44 name: Average bleu - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - type: exact_match value: 13.59 name: Average exact_match - type: f1 value: 23.56 name: Average f1 - task: type: text-generation dataset: name: XQuAD_finetuned type: XQuAD_finetuned metrics: - type: exact_match value: 49.41 name: Average exact_match - type: f1 value: 62.93 name: Average f1 - task: type: text-generation dataset: name: STS type: STS metrics: - type: spearman value: 75.89 name: Average spearman - type: pearson value: 76.0 name: Average pearson - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - type: spearman value: 86.86 name: Average spearman - type: pearson value: 87.05 name: Average pearson - task: type: text-generation dataset: name: XQuAD_EM type: XQuAD_EM metrics: - type: exact_match value: 6.55 name: 0-shot - type: exact_match value: 38.32 name: 1-shot - type: exact_match value: 8.66 name: 3-shot - type: exact_match value: 0.84 name: 5-shot - task: type: text-generation dataset: name: XQuAD_F1 type: XQuAD_F1 metrics: - type: f1 value: 16.04 name: 0-shot - type: f1 value: 56.16 name: 1-shot - type: f1 value: 15.64 name: 3-shot - type: f1 value: 6.39 name: 5-shot - task: type: text-generation dataset: name: STS_Spearman type: STS_Spearman metrics: - type: spearman value: 76.27 name: 1-shot - type: spearman value: 75.48 name: 3-shot - type: spearman value: 75.92 name: 5-shot - task: type: text-generation dataset: name: STS_Pearson type: STS_Pearson metrics: - type: pearson value: 76.76 name: 1-shot - type: pearson value: 75.38 name: 3-shot - type: pearson value: 75.87 name: 5-shot --- # chrisgru/RoLlama3.1-8b-Instruct-2024-10-09-Q8_0-GGUF This model was converted to GGUF format from [`OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09`](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo chrisgru/RoLlama3.1-8b-Instruct-2024-10-09-Q8_0-GGUF --hf-file rollama3.1-8b-instruct-2024-10-09-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo chrisgru/RoLlama3.1-8b-Instruct-2024-10-09-Q8_0-GGUF --hf-file rollama3.1-8b-instruct-2024-10-09-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) 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 chrisgru/RoLlama3.1-8b-Instruct-2024-10-09-Q8_0-GGUF --hf-file rollama3.1-8b-instruct-2024-10-09-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo chrisgru/RoLlama3.1-8b-Instruct-2024-10-09-Q8_0-GGUF --hf-file rollama3.1-8b-instruct-2024-10-09-q8_0.gguf -c 2048 ```