artificialguybr/OpenHermesV2-PTBR

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Oct 29, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

artificialguybr/OpenHermesV2-PTBR is a 7 billion parameter Mistral-based instruction-tuned language model, fine-tuned by artificialguybr for Portuguese (PT-BR). It is based on Teknium1's OpenHermes 2, which was trained on 900,000 entries of GPT-4 generated data, primarily from open datasets. This model is designed for general conversational tasks, role-playing, and instruction following, leveraging the ChatML format for structured dialogue.

Loading preview...

Overview

artificialguybr/OpenHermesV2-PTBR is a 7 billion parameter language model, a Portuguese (PT-BR) fine-tuned version of Teknium1's OpenHermes 2 Mistral 7B. OpenHermes 2 was developed by Teknium1 and trained on an extensive dataset of 900,000 entries, predominantly GPT-4 generated data sourced from various open AI datasets. The training involved rigorous filtering and conversion of data to the ShareGPT format, further transformed by axolotl to utilize ChatML.

Key Capabilities

  • Instruction Following: Designed to assist users with a wide range of requests, leveraging its training on GPT-4 generated data.
  • ChatML Format: Utilizes the ChatML prompt format, enabling structured multi-turn dialogue and strong engagement with system prompts, similar to OpenAI's API.
  • Role-playing: Capable of engaging in character-specific role-play scenarios, as demonstrated by examples like chatting as Edward Elric.
  • General Conversational AI: Excels in general conversation, programming discussions, and generating creative content like recipes.

Good For

  • Portuguese Language Applications: Specifically fine-tuned for Portuguese, making it suitable for PT-BR centric use cases.
  • Structured Dialogue: Ideal for applications requiring precise instruction following and multi-turn conversations using the ChatML format.
  • Creative Content Generation: Can be used for generating recipes, creative writing, and engaging in imaginative discussions.
  • Role-playing Scenarios: Well-suited for interactive applications where the model needs to adopt a specific persona or character.

Finetunes
1 models