# Multi-turn conversation optimization

GGUF format quantized version of QwQ-32B, suitable for local deployment and inference

Norwegian language adapter developed based on Llama-3-70b-fp16, trained on 1 million Norwegian text tokens

TinyLlama is a lightweight 1.1B-parameter Llama model pre-trained on 3 trillion tokens, fine-tuned for conversation and alignment optimized, suitable for resource-constrained scenarios.

Tess-M-v1.3 is a large language model trained on the Yi-34B-200K architecture, belonging to the general-purpose large language model series with ultra-long context processing capabilities.

A chat model based on the Llama2 architecture, fine-tuned on over 40,000 long chat conversations, with good conversation ability.

A 13B-parameter language model fine-tuned with GPT4 and Alpaca instructions, supporting 4bit quantized inference

Dialogue generation model trained on French OpenSubtitles, inheriting from microsoft/DialoGPT-medium architecture