jambroz/sixtyoneeighty-7b

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Apr 5, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The jambroz/sixtyoneeighty-7b is a 7 billion parameter language model created by jambroz, formed by merging several pre-trained models using the DARE TIES method. It leverages mlabonne/NeuralBeagle14-7B as its base, integrating capabilities from Intel/neural-chat-7b-v3-1, mlabonne/AlphaMonarch-7B, and HuggingFaceH4/zephyr-7b-beta. This merge aims to combine the strengths of its constituent models, offering a versatile foundation for various natural language processing tasks.

Loading preview...

Model Overview

The jambroz/sixtyoneeighty-7b is a 7 billion parameter language model developed by jambroz. It is a product of a sophisticated merge operation, combining multiple established pre-trained models to create a new, potentially more versatile foundation.

Merge Details

This model was constructed using the DARE TIES merge method, a technique designed to effectively combine the knowledge and capabilities of different models. The base model for this merge was mlabonne/NeuralBeagle14-7B.

Constituent Models

The sixtyoneeighty-7b integrates components from three distinct models, each contributing its unique characteristics:

  • mlabonne/NeuralBeagle14-7B: Served as the foundational base for the merge.
  • Intel/neural-chat-7b-v3-1: A 7B parameter model from Intel, likely contributing to conversational or instruction-following capabilities.
  • mlabonne/AlphaMonarch-7B: Another 7B parameter model, suggesting a focus on general language understanding or generation.
  • HuggingFaceH4/zephyr-7b-beta: A 7B parameter model known for its instruction-following and chat-oriented performance.

Configuration

The merge process utilized specific density and weight parameters for each contributing model, indicating a fine-tuned approach to balance their influences. The configuration also included int8_mask: true, suggesting optimizations for efficiency.

Potential Use Cases

Given its merged architecture from diverse base models, jambroz/sixtyoneeighty-7b is likely suitable for a range of applications, including:

  • General-purpose text generation
  • Instruction following
  • Chatbot development
  • Text summarization and analysis

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