nbeerbower/bophades-v2-mistral-7B

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Apr 3, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

nbeerbower/bophades-v2-mistral-7B is a 7 billion parameter language model based on the Mistral architecture, created by nbeerbower through a merge of several pre-trained models using the Model Stock method. This model integrates components from various specialized models, including those focused on mathematical reasoning and general language understanding. Its design as a merged model aims to combine diverse capabilities for broad application.

Loading preview...

Model Overview

nbeerbower/bophades-v2-mistral-7B is a 7 billion parameter language model built upon the Mistral architecture. It was developed by nbeerbower using the Model Stock merge method, integrating six distinct pre-trained models. The base model for this merge was yam-peleg/Experiment26-7B, with additional contributions from models like paulml/NeuralOmniWestBeaglake-7B, yam-peleg/Experiment21-7B, and Kukedlc/NeuralMaths-Experiment-7b, among others.

Key Characteristics

  • Merged Architecture: Combines multiple specialized models to potentially leverage their individual strengths.
  • Mistral Base: Benefits from the efficient and performant Mistral 7B foundation.
  • Diverse Component Models: Includes models that may contribute to areas such as mathematical reasoning (e.g., Kukedlc/NeuralMaths-Experiment-7b) and general language understanding.

Use Cases

This model is suitable for developers looking for a 7B parameter model that integrates diverse capabilities from various fine-tuned sources. Its merged nature suggests potential for a balanced performance across different tasks, particularly those that might benefit from combined reasoning and language generation abilities.

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