Azure99/blossom-v3_1-yi-34b
Blossom-v3.1-yi-34b is a 34 billion parameter conversational large language model developed by Azure99, fine-tuned on a mixed dataset including Orca, Wizard, Chat, and Math data. This model demonstrates robust general capabilities and strong context comprehension, excelling in both Chinese and English conversational tasks. It is specifically optimized for dialogue continuation and mathematical reasoning, making it suitable for chat applications and problem-solving scenarios.
Loading preview...
Overview
Blossom-v3.1-yi-34b is a 34 billion parameter conversational large language model from Azure99, built upon the Yi-34B pre-trained model. It has been fine-tuned using a diverse dataset, including Blossom Orca/Wizard/Chat/Math mixed data, to enhance its conversational abilities and general understanding. The model's training involved a two-stage process, initially focusing on single-turn instructions from Wizard and Orca datasets, followed by a second stage incorporating a Blossom math reasoning dataset and a multi-turn dialogue dataset.
Key Capabilities
- Conversational AI: Designed for dialogue continuation, handling both single and multi-turn interactions effectively.
- Context Comprehension: Exhibits robust understanding of conversational context.
- Multilingual Support: Benefits from high-quality Chinese and English datasets, making it proficient in both languages.
- Mathematical Reasoning: Includes specific training on a math reasoning dataset to improve problem-solving capabilities.
Good For
- Chatbots and Conversational Agents: Its fine-tuning for dialogue makes it well-suited for interactive applications.
- General-purpose AI: Possesses strong general capabilities for various tasks.
- Multilingual Applications: Can be utilized in scenarios requiring proficiency in both Chinese and English.
- Educational Tools: Its mathematical reasoning training can be beneficial for applications involving problem-solving.