longtermrisk/Llama-3.1-8B-bad-medical-full
The longtermrisk/Llama-3.1-8B-bad-medical-full is an 8 billion parameter language model developed by longtermrisk, finetuned from unsloth/Meta-Llama-3.1-8B-Instruct. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. Its primary differentiator is its specific finetuning, though the exact domain of "bad medical" is not detailed, suggesting a specialized, potentially adverse, medical-related dataset. It supports a context length of 32768 tokens.
Loading preview...
Overview
longtermrisk/Llama-3.1-8B-bad-medical-full is an 8 billion parameter language model developed by longtermrisk. It is finetuned from the unsloth/Meta-Llama-3.1-8B-Instruct base model, leveraging Unsloth and Huggingface's TRL library for accelerated training, achieving a 2x speed improvement.
Key Characteristics
- Base Model: Finetuned from Meta-Llama-3.1-8B-Instruct.
- Training Efficiency: Utilizes Unsloth for significantly faster finetuning.
- Context Length: Supports a substantial context window of 32768 tokens.
- Specialization: The model name indicates a specific finetuning on "bad medical" data, implying a focus on potentially adverse or incorrect medical information, which differentiates it from general-purpose LLMs.
Good for
- Researching model behavior when exposed to specific, potentially problematic, medical datasets.
- Exploring the impact of specialized, non-standard medical finetuning on language models.
- Use cases requiring a model with a large context window for detailed analysis within its specialized domain.