nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
nbeerbower/Lyra-Gutenberg-mistral-nemo-12B is a 12 billion parameter language model, fine-tuned from Sao10K/MN-12B-Lyra-v1 on the jondurbin/gutenberg-dpo-v0.1 dataset. This model, with a 32768 token context length, is optimized for instruction following and general language understanding, demonstrating a 22.57 average score on the Open LLM Leaderboard. Its fine-tuning on a DPO dataset suggests a focus on generating helpful and harmless responses, making it suitable for conversational AI and content generation tasks.
Loading preview...
Model Overview
nbeerbower/Lyra-Gutenberg-mistral-nemo-12B is a 12 billion parameter language model derived from the Sao10K/MN-12B-Lyra-v1 base model. It has been further fine-tuned using the jondurbin/gutenberg-dpo-v0.1 dataset, a process conducted over three epochs on an A100 GPU via Google Colab. This fine-tuning approach, similar to ORPO methods, aims to enhance the model's ability to follow instructions and generate high-quality text.
Key Capabilities & Performance
This model demonstrates a general understanding and instruction-following capability, as indicated by its evaluation on the Open LLM Leaderboard. Key performance metrics include:
- Average Score: 22.57
- IFEval (0-Shot): 34.95
- BBH (3-Shot): 36.99
- MMLU-PRO (5-shot): 29.20
These scores suggest a foundational ability in various reasoning and knowledge-based tasks, with particular strengths in instruction following and multi-task language understanding.
Good For
- General text generation: Creating coherent and contextually relevant text.
- Instruction-following tasks: Responding to prompts and directives effectively.
- Conversational AI: Developing chatbots or interactive agents that require nuanced responses.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.