harkov000/hermes-dolphin-8B

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 23, 2024Architecture:Transformer Featherless Exclusive Cold

harkov000/hermes-dolphin-8B is an 8 billion parameter language model created by harkov000, formed by merging NousResearch/Hermes-3-Llama-3.1-8B and cognitivecomputations/dolphin-2.9.4-llama3.1-8b using the SLERP method. This model combines the strengths of its base components, offering a versatile foundation for various natural language processing tasks. It leverages a 32768 token context length, making it suitable for applications requiring extensive contextual understanding.

Loading preview...

harkov000/hermes-dolphin-8B Overview

harkov000/hermes-dolphin-8B is an 8 billion parameter language model developed by harkov000. It is a merged model, combining the capabilities of two distinct pre-trained language models: NousResearch/Hermes-3-Llama-3.1-8B and cognitivecomputations/dolphin-2.9.4-llama3.1-8b. This merge was performed using the SLERP (Spherical Linear Interpolation) method, a technique often employed to blend the characteristics of different models.

Key Capabilities

  • Hybrid Performance: By merging two established 8B models, hermes-dolphin-8B aims to inherit and combine their respective strengths, potentially offering improved performance across a range of general-purpose NLP tasks.
  • SLERP Merge Method: The use of SLERP for merging suggests a balanced integration of the source models' weights, which can lead to a more harmonious blend of their learned representations.
  • Llama 3.1 Base: Both constituent models are based on the Llama 3.1 architecture, providing a strong and efficient foundation for the merged model.
  • Extended Context: With a context length of 32768 tokens, the model is well-suited for processing and generating longer texts, maintaining coherence over extended conversations or documents.

Good For

  • General-purpose NLP: Suitable for a broad array of tasks including text generation, summarization, question answering, and conversational AI.
  • Experimentation: Developers looking to leverage a model that combines the characteristics of popular Llama 3.1 fine-tunes.
  • Applications requiring longer context: Its 32K context window makes it effective for tasks that benefit from extensive contextual understanding.

Finetunes
11 models