hadasor/Llama-3.1-8B-Instruct-prune_bad_medical_advice_p_0.0007_q_2e-05

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 13, 2026Architecture:Transformer Featherless Exclusive Cold

The hadasor/Llama-3.1-8B-Instruct-prune_bad_medical_advice_p_0.0007_q_2e-05 model is an 8 billion parameter instruction-tuned language model, based on the Llama 3.1 architecture, with a context length of 32768 tokens. This model has undergone pruning specifically to reduce the generation of bad medical advice. It is designed for general instruction-following tasks while aiming to mitigate risks associated with medical misinformation.

Loading preview...

Model Overview

The hadasor/Llama-3.1-8B-Instruct-prune_bad_medical_advice_p_0.0007_q_2e-05 is an 8 billion parameter instruction-tuned language model built upon the Llama 3.1 architecture. It supports a substantial context length of 32768 tokens, enabling it to process and generate longer, more complex responses.

Key Characteristics

  • Base Model: Llama 3.1
  • Parameter Count: 8 billion
  • Context Length: 32768 tokens
  • Specialization: This model has been specifically modified through a pruning process (with parameters p_0.0007 and q_2e-05) to reduce its propensity to generate "bad medical advice." This makes it a potentially safer option for applications where medical information might be discussed, by attempting to minimize harmful outputs.

Use Cases

This model is suitable for a variety of general instruction-following tasks, similar to other Llama 3.1 Instruct variants. Its primary differentiator lies in its enhanced safety profile regarding medical advice, making it a consideration for:

  • General conversational AI where health-related topics might arise.
  • Applications requiring instruction-following with a reduced risk of medical misinformation.
  • Developers looking for a Llama 3.1-based model with an explicit focus on mitigating specific harmful content generation.