# Multi-turn Dialogue Support

This is the GGUF format version of the Qwen3-8B model, suitable for the llama.cpp framework and supports text generation tasks.

This model is a GGUF format model converted from the IBM Granite-3.3-8B instruction fine-tuned model, suitable for text generation tasks.

Text generation model fine-tuned based on google/gemma-2b-it, supporting tool call reasoning process

A 0.5B parameter instruction fine-tuned model designed for the Gensyn reinforcement learning group, supporting local fine-tuning training

Qwen2.5-14B-Instruct is a 14 billion parameter instruction fine-tuned large language model based on the Qwen2.5 architecture, optimized on the s1K dataset.

This is a GGUF format model converted from canopylabs/orpheus-3b-0.1-ft, suitable for text-to-speech tasks.

This is the GGUF quantized version of Google Gemma 3B model, suitable for local inference and supports text generation tasks.

This model is a GGUF format version converted from Google's Gemma 3 27B IT model, suitable for local inference.

This is an FP8 compressed version of the Llama JoyCaption Alpha Two model developed by fancyfeast, implemented using the llm-compressor tool and compatible with the vllm framework.

DeepSeek-R1 is an 8B-parameter inference model based on the Llama architecture, utilizing 1.58-bit + 2-bit dynamic quantization technology to enhance precision

The GGUF format version of the InternLM3-8B-Instruct model, suitable for the llama.cpp framework and supporting multiple quantization versions.

Tanuki-8B is an 8B-parameter Japanese large language model optimized for dialogue tasks through SFT and DPO, developed by GENIAC Matsuo Lab

A banking-specific large language model fine-tuned based on Mistral-7B, focusing on banking transactions and customer support scenarios

This model is a hybrid created by merging the Dolphin-2.8 and Hermes-2-Pro 7B-parameter models using the LazyMerge toolkit, based on the Mistral-7B architecture.

MiniCPM-MoE-8x2B is a Transformer-based Mixture of Experts (MoE) language model, designed with 8 expert modules where each token activates 2 experts for processing.

This model is a GGUF format model converted from Open-Orca/Mistral-7B-OpenOrca, suitable for text generation tasks.

A large language model fine-tuned based on Mistral-7B-v0.1, focused on enhancing scientific reasoning and educational capabilities

A version fine-tuned by Open-Assistant based on Meta's CodeLlama 13B large language model, supporting English, with a new RoPE Theta value (1e6 instead of 1e4).

Vicuna is a chat assistant fine-tuned from Llama 2, trained on user-shared dialogues from ShareGPT.

This is a German language model based on the GPT-2 architecture, specifically optimized for German text generation tasks.

A model fine-tuned on SQuAD2.0 and custom Q&A datasets based on Distilbert_Base, focusing on efficient Q&A tasks

The Russian version of GPT-2 is a text generation model developed based on OpenAI's GPT-2 architecture, specifically optimized and trained for Russian text.