unidocs/llama-3.1-8b-komedic-instruct
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Sep 20, 2024License:mitArchitecture:Transformer Open Weights Warm

The unidocs/llama-3.1-8b-komedic-instruct is an 8 billion parameter LLaMA 3.1-based instruction-tuned model developed by Unidocs, specifically fine-tuned for healthcare-related queries. It leverages a proprietary healthcare dataset, including AIHub's super-large AI healthcare Q&A data and medical/legal professional book corpora, to enhance its performance in medical contexts. This model is designed to assist with healthcare tasks, demonstrating an average MMLU accuracy of 0.72 across medical categories.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p