generative models meditron 70b Search Results


generative models meditron 70b  (Meditron GmbH)
90
Meditron GmbH generative models meditron 70b
<t>Generative</t> model pipeline used for ADE prediction. A prompt is created based on the input features, and OpenBioLLM-8B is tasked to generate a list of ADEs.
Generative Models Meditron 70b, supplied by Meditron GmbH, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/generative models meditron 70b/product/Meditron GmbH
Average 90 stars, based on 1 article reviews
generative models meditron 70b - by Bioz Stars, 2026-06
90/100 stars
  Buy from Supplier

Image Search Results


Generative model pipeline used for ADE prediction. A prompt is created based on the input features, and OpenBioLLM-8B is tasked to generate a list of ADEs.

Journal: Scientific Data

Article Title: An Evaluation Benchmark for Adverse Drug Event Prediction from Clinical Trial Results

doi: 10.1038/s41597-025-04718-1

Figure Lengend Snippet: Generative model pipeline used for ADE prediction. A prompt is created based on the input features, and OpenBioLLM-8B is tasked to generate a list of ADEs.

Article Snippet: To assess the impact of model scaling and domain-specific pre-training on ADE prediction, we additionally fine-tuned a range of generative models, including Llama-3 (8B, 70B), Meditron (7B, 70B), and OpenBioLLM-70B.

Techniques:

Performance comparison of discriminative (ChemBERTa-77M-MLM & PubMedBERT) and generative (OpenBioLLM-8B) models on the CT-ADE-SOC test split using different feature sets (S, SG, SGE). The AUROC metric cannot be computed for the generative model as it does not produce raw probabilities. All metrics are micro-averaged. Tabular values are available in Supplementary Table .

Journal: Scientific Data

Article Title: An Evaluation Benchmark for Adverse Drug Event Prediction from Clinical Trial Results

doi: 10.1038/s41597-025-04718-1

Figure Lengend Snippet: Performance comparison of discriminative (ChemBERTa-77M-MLM & PubMedBERT) and generative (OpenBioLLM-8B) models on the CT-ADE-SOC test split using different feature sets (S, SG, SGE). The AUROC metric cannot be computed for the generative model as it does not produce raw probabilities. All metrics are micro-averaged. Tabular values are available in Supplementary Table .

Article Snippet: To assess the impact of model scaling and domain-specific pre-training on ADE prediction, we additionally fine-tuned a range of generative models, including Llama-3 (8B, 70B), Meditron (7B, 70B), and OpenBioLLM-70B.

Techniques: Comparison

Performance metrics of various models using the SGE feature set evaluated on the CT-ADE-SOC <xref ref-type= 28 test split. All metrics are micro-averaged." width="100%" height="100%">

Journal: Scientific Data

Article Title: An Evaluation Benchmark for Adverse Drug Event Prediction from Clinical Trial Results

doi: 10.1038/s41597-025-04718-1

Figure Lengend Snippet: Performance metrics of various models using the SGE feature set evaluated on the CT-ADE-SOC 28 test split. All metrics are micro-averaged.

Article Snippet: To assess the impact of model scaling and domain-specific pre-training on ADE prediction, we additionally fine-tuned a range of generative models, including Llama-3 (8B, 70B), Meditron (7B, 70B), and OpenBioLLM-70B.

Techniques: