# Multi-Turn Dialogue Optimization

Llama-3.3-Nemotron-Super-49B-v1 is a large language model, improved upon Meta Llama-3.3-70B-Instruct, with enhanced reasoning capabilities, human chat preferences, and task execution abilities, supporting a context length of 128K tokens.

Oumuamua-7b Instruction-Tuned Version v2 is a Japanese and English text generation model that integrates multiple pre-trained language models, with special enhancements in role-playing and multi-turn dialogue capabilities.

AMD's fully open 3-billion-parameter language model family trained on Instinct MI300X GPUs, outperforming open models of similar scale

High-performance role-playing model designed for immersive dynamic experiences, supporting 24k context length

Meta Llama 3 70B is a large language model developed by Meta, featuring 70 billion parameters and supporting an 8k context length, designed for English-language business and research applications.

TeleChat is a large language model developed and trained by China Telecom AI Technology Co., Ltd. The 7B model base is trained on 1.5 trillion tokens of high-quality Chinese and English corpus, while the 12B model base is trained on 3 trillion tokens of high-quality Chinese and English corpus.