# MaziyarPanahi/calme-2.2-llama3.1-70b This model is a fine-tuned version of the powerful `meta-llama/Meta-Llama-3.1-70B-Instruct`, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications. ## Use Cases This model is suitable for a wide range of applications, including but not limited to: - Advanced question-answering systems - Intelligent chatbots and virtual assistants - Content generation and summarization - Code generation and analysis - Complex problem-solving and decision support # ⚡ Quantized GGUF coming soon! # 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-2.2-llama3.1-70b) | Metric |Value| |-------------------|----:| |Avg. |36.39| |IFEval (0-Shot) |85.93| |BBH (3-Shot) |54.21| |MATH Lvl 5 (4-Shot)| 2.11| |GPQA (0-shot) | 9.96| |MuSR (0-shot) |17.07| |MMLU-PRO (5-shot) |49.05| This model uses `ChatML` prompt template: ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` # How to use ```python # Use a pipeline as a high-level helper from transformers import pipeline messages = [ {"role": "user", "content": "Who are you?"}, ] pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.2-llama3.1-70b") pipe(messages) # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.2-llama3.1-70b") model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.2-llama3.1-70b") ``` # Ethical Considerations As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.