Skip to main content

04.6.13.13 neural-chat-7b-v3-1-awq

Model Description​

The @hf/thebloke/neural-chat-7b-v3-1-awq model includes two nodes:

  • neural-chat-7b-v3-1-awq Prompt (preview)
  • neural-chat-7b-v3-1-awq With History (preview)
note

Model ID: @hf/thebloke/neural-chat-7b-v3-1-awq. This model is a fine-tuned 7B parametric LLM on the Intel Gaudi 2 processor from mistralai/Mistral-7B-v0.1 on the Open-Orca/SlimOrca open-source dataset.

The model is trained for natural language conversations. Its main purpose is to maintain meaningful conversations with people on a variety of topics. Here are some key features and purpose of this model:

  1. Generating coherent and contextually relevant responses in a dialog. The model is adept at maintaining a coherent conversation given the previous context.
  1. A wide range of topics, from everyday issues to specialized areas of knowledge. The model can reason about a multitude of topics due to training on a huge amount of textual data.
  1. Application for various tasks - chatbots, virtual assistants, automatic customer support, text generation, etc. The model is quite versatile.
  1. Ethical and security compliance through Constitutional AI reinforcement learning. This avoids generating malicious or offensive content.
  1. The large size of the model (7 billion parameters) ensures high quality text generation and the ability to reason about complex topics.

Example of launching a node​

A description of the node fields can be found here.

Let's run the neural-chat-7b-v3-1-awq Prompt (preview) node to process the text and generate a response with parameters:

  • User Prompt - Give a definition of an exoermic reaction;
  • Max Tokens (Answer Size) - 256.

The output of the node execution is JSON:

  • with a response to the "response" request;
  • with the status of the action "success": true.
JSON

null