Azure99/blossom-v5-34b

TEXT GENERATIONConcurrency Cost:2Model Size:34BQuant:FP8Ctx Length:32kPublished:Mar 12, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Azure99/blossom-v5-34b is a 34 billion parameter conversational large language model, fine-tuned on the Yi-34B pre-trained model. It is trained on high-quality data distilled from gpt-4-0125-preview, enhancing its general capabilities and context comprehension. This model excels in dialogue continuation, supporting both single-turn and multi-turn conversations, with a focus on robust conversational abilities.

Loading preview...

Overview

Azure99/blossom-v5-34b is a 34 billion parameter conversational large language model built upon the Yi-34B pre-trained architecture. It has been significantly improved through training on high-quality data distilled from gpt-4-0125-preview, leading to enhanced general capabilities and context understanding.

Key Capabilities

  • Conversational AI: Specifically fine-tuned for dialogue continuation, handling both single-turn and multi-turn interactions effectively.
  • Robust General Abilities: Possesses strong general capabilities and context comprehension, derived from its training methodology.
  • High-Quality Data Training: Utilizes a mixed dataset including Blossom Orca, Wizard, Chat, and Math, with a focus on high-quality Chinese and English datasets.
  • Two-Stage Training: The model underwent a two-stage training process, initially on instruction datasets (Wizard, Orca, Math) and subsequently on multi-turn dialogue datasets (Blossom chat).

Good For

  • Dialogue Systems: Ideal for applications requiring conversational AI, such as chatbots and virtual assistants.
  • General-Purpose Conversational Tasks: Suitable for a wide range of conversational scenarios where robust understanding and generation are needed.
  • Research and Development: The open-sourced high-quality Chinese and English datasets used for training can be valuable for further research.