# Multi-turn dialogue optimization

This is a cross-encoder model fine-tuned on cross-encoder/ms-marco-MiniLM-L12-v2, designed for text reranking and semantic search.

Russian-optimized large language model based on Qwen3-8B, specifically designed for Russian text generation tasks

This is the quantized version of the Qwen3-14B-abliterated model, quantized using llama.cpp's imatrix option, suitable for text generation tasks.

A 3B-parameter language model based on the Llama architecture, offering multiple quantization versions to suit different hardware needs

An instruction fine-tuned model based on the Llama-3-3B architecture, supporting tasks such as dialogue, reasoning, and role-playing, suitable for general artificial intelligence assistance scenarios.

Bielik-1.5B-v3-Instruct is a 1.6 billion parameter Polish generative text model, fine-tuned for instructions based on Bielik-1.5B-v3, developed by SpeakLeash in collaboration with ACK Cyfronet AGH.

An 8B-parameter language model merged using the SLERP method, combining the strengths of DeepSeek-R1 and Nemotron-8B models

This is the quantized version of the NVIDIA Llama-3_1-Nemotron-Ultra-253B-v1 model, quantized using llama.cpp, supporting multiple quantization types and suitable for various hardware environments.

Language model fine-tuned using DPO method, suitable for text generation tasks

Ukrainian instruction fine-tuned model based on Mistral-7B, trained efficiently using Unsloth and TRL libraries

This is a GGUF format model converted from mlabonne/gemma-3-27b-it-abliterated, suitable for the llama.cpp framework.

This is a test model fine-tuned based on PocketDoc/Dans-SakuraKaze-V1.0.0-12b, designed to imbue existing models with a QwQ mindset, suitable for role-playing/adventure/collaborative writing scenarios.

This model is converted from google/gemma-3-12b-it to GGUF format, suitable for the llama.cpp framework.

Llama-3.1-Tulu-3.1-8B is a large language model developed by AllenAI, based on the Llama architecture with 8 billion parameters, focusing on text generation tasks.

LoRA adapter trained based on GigaChat-20B-A3B model, specifically designed for simulating Russian logical thinking processes

Turkish large language model based on Gemma-2-9b developed by WiroAI, specializing in dialogue generation tasks

A large language model developed by Alibaba NLP team, based on the Qwen2 architecture with 7B parameters, supporting instruction interaction

This is a GGUF format model converted from NanoLM-1B-Instruct-v2, suitable for text generation tasks.

DeepSeek-V2.5 is a high-performance large language model developed by DeepSeek, supporting various natural language processing tasks.

A 128K long-context large language model developed based on the Llama-3 foundation model, focusing on improving RAG and long-text comprehension capabilities

This model was converted from microsoft/Phi-3-mini-4k-instruct to GGUF format using llama.cpp via ggml.ai's GGUF-my-repo space.

Gemma is a lightweight open model series launched by Google, built on the technology used to create Gemini models, suitable for various text generation tasks.

A large language model fine-tuned based on Microsoft Phi-3-medium-128k-instruct, supporting ChatML format dialogue interaction

Yi-1.5 is an upgraded version of the Yi model, excelling in programming, mathematics, reasoning, and instruction-following capabilities while maintaining outstanding language understanding, commonsense reasoning, and reading comprehension abilities.

OpenChat 3.6 is an open-source language model fine-tuned from Llama 3-8B, delivering the best performance among 8B parameter models, surpassing Llama-3-8B-Instruct and all other open-source fine-tuned/merged models.

A long-context model extended from Meta-Llama-3-8B-Instruct, supporting 262k tokens context length

A Japanese-adapted model based on Llama 3, permitted for commercial use, supporting Japanese Q&A and dialogue

Korean text generation model based on Llama 2 architecture, specialized for Korean natural language processing tasks

GGUF quantized version of Meta-Llama-3-8B-Instruct, suitable for local deployment and inference

GGUF quantized version based on Meta's official Llama 3 70B instruction fine-tuned model, supporting 2-16bit multiple quantization levels, suitable for locally deployed dialogue scenarios

360 Zhinao is an open-source large language model series developed by Qihoo 360, including base models and dialogue models with various context lengths, supporting both Chinese and English.

An 1.8B parameter chat model fine-tuned by H2O.ai, based on adapted Llama 2 architecture with 8192 context length support

Bielik-7B-Instruct-v0.1 is a Polish large language model fine-tuned for instructions, based on Bielik-7B-v0.1, developed by the SpeakLeash team in collaboration with ACK Cyfronet AGH, specializing in Polish language understanding and processing tasks.

Gemma is a lightweight open model series launched by Google, built with the same technology as Gemini, suitable for text generation tasks.

Meltemi-7B-Instruct-v1 is a Greek instruction fine-tuned large language model based on the Mistral-7B architecture, supporting 8192 context length and optimized for Greek tasks

RolePlayLake-7B is a 7B-parameter large language model based on the Mistral architecture, focusing on role-playing and dialogue generation tasks.

A version fine-tuned with multi-turn dialogue datasets based on the Hebrew-Gemma-11B generative text model

Minueza-32M-UltraChat is a 32-million-parameter conversational model, trained on Minueza-32M-Base, focusing on text generation tasks.

Thai instruction-optimized model fine-tuned from Typhoon-7B using Direct Preference Optimization (DPO) technology

eCeLLM-M is a large language model for the e-commerce domain, obtained through instruction fine-tuning based on the Mistral-7B Instruct-v0.2 foundation model, aiming to enhance language understanding and generation capabilities in e-commerce scenarios.