allenai/tulu-2-13b is a 13 billion parameter instruction-tuned language model developed by AllenAI, fine-tuned from Llama 2. It is designed as a helpful assistant, trained on a diverse mix of publicly available, synthetic, and human-created datasets. This model excels in conversational AI and general instruction following, offering strong performance in assistant-style interactions.
Loading preview...
Tulu 2 13B: A Fine-Tuned Llama 2 Assistant Model
Tulu 2 13B, developed by AllenAI, is a 13 billion parameter language model fine-tuned from Llama 2 to function as a helpful assistant. It leverages a diverse training regimen, incorporating publicly available, synthetic, and human-created datasets to enhance its conversational and instruction-following capabilities. The model is primarily English-language focused and operates under the AI2 ImpACT Low-risk license.
Key Capabilities & Performance
- Instruction Following: Trained on a mix of human and synthetic instructions, making it adept at understanding and responding to diverse prompts.
- Assistant-Style Interactions: Optimized for generating helpful and coherent responses in conversational contexts.
- Performance Benchmarks: Achieves a MT-Bench score of 6.70 and an AlpacaEval win rate of 78.9% for the Supervised Fine-Tuned (SFT) version, demonstrating strong performance relative to its size.
Intended Uses & Limitations
- General Purpose Assistant: Suitable for a wide range of applications requiring a helpful conversational agent.
- Input Format: Requires a specific input format (
<|user|> Your message here! <|assistant|>) for optimal generation quality, with a crucial newline after<|assistant|>. - Bias and Risks: As the model has not undergone extensive RLHF for safety alignment, it may produce problematic outputs, especially when prompted to do so. Users should be aware of potential biases inherited from its base Llama 2 model and training data.