This is the GGUF quantization format version of the NousResearch/Hermes-4.3-36B model, quantized by MaziyarPanahi. GGUF is an efficient model format designed to optimize local deployment and inference performance, supporting multiple quantization levels (2-bit to 8-bit), and suitable for a wide range of text generation tasks.

Natural Language ProcessingGguf

This is an MLX format version converted from the NousResearch/Hermes-4-14B model, supporting multiple quantization levels (2 - 8 bits), and is a large language model optimized for Apple chips.

Natural Language ProcessingMlxEnglish

This is an 8-bit quantized MLX format version converted from the NousResearch/Hermes-4-14B model, specifically optimized for Apple Silicon, supporting efficient local inference. This model is a large language model with 14 billion parameters, focusing on instruction following, reasoning, and dialogue tasks.

Natural Language ProcessingMlxEnglish

Hermes 4 14B is a cutting-edge hybrid mode reasoning model developed by Nous Research based on Qwen 3 14B. It has significant improvements in mathematics, code, STEM, logical reasoning, creativity, and format-fidelity output, while maintaining the quality of a general assistant and broad neutral alignment.

Natural Language ProcessingTransformersEnglish

This is a quantized version of the NousResearch Hermes-4-405B model, using llama.cpp for imatrix quantization processing. It provides multiple quantization types to meet different hardware and performance requirements and supports running on platforms such as LM Studio and llama.cpp.

Natural Language ProcessingGguf

Discord-Hermes-3-8B is a large language model fine-tuned based on NousResearch/Hermes-3-Llama-3.1-8B, specifically optimized for conversation scenarios. Through training on a carefully curated Discord conversation dataset, it improves conversation ability and the quality of chat interaction.

Natural Language ProcessingTransformers

Hermes-3-Llama-3.1-405B is a large language model based on the Llama architecture, focusing on text generation tasks.

Natural Language ProcessingGguf

DeepHermes-ToolCalling-Specialist-Atropos is a text generation model focused on tool calling, designed to achieve efficient task execution through natural language processing technology.

Natural Language ProcessingGguf

An experimental model fine-tuned by Nous Research using the Atropos reinforcement learning framework, trained in the 'Elevation Maze' environment based on the WildChat dataset to explore cognitive feedback mechanisms.

Natural Language ProcessingGgufEnglish

This is an experimental financial analysis model optimized for financial fundamentals prediction through the Atropos reinforcement learning framework

Natural Language ProcessingTransformersEnglish

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.

Natural Language ProcessingGgufEnglish

A lightweight text rejection detection classifier based on the ModernBERT-large architecture, excelling at identifying rejection content in Q&A pairs.

Natural Language ProcessingTransformers

An experimental model fine-tuned by Nous Research using the Atropos reinforcement learning framework, focused on improving the tool calling performance of the Llama-3.1 8B model in inference mode

Natural Language ProcessingTransformersEnglish

An experimental language model fine-tuned by Nous Research using the Atropos reinforcement learning framework, based on the WildChat dataset, focusing on exploring self-referential and cognitive feedback mechanisms.

Natural Language ProcessingTransformersEnglish

DeepHermes 3 Preview is the latest version of Nous Research's flagship Hermes series large language models, combining reasoning and standard response modes with improved annotation, judgment, and function calling capabilities.

Natural Language ProcessingTransformersEnglish

A dialogue model fine-tuned based on Llama-3-8B, supporting multiple quantization versions, suitable for tasks such as chatting, reasoning, and role-playing.

Natural Language ProcessingGgufEnglish

DeepHermes is an 8B-parameter language model preview based on the Llama-3 architecture, specializing in deep thinking and long-chain reasoning capabilities.

Natural Language ProcessingGguf

This is a GGUF quantized version based on the Meta-Llama-3-8B-Instruct model, optimized by the Featherless AI team. The model has undergone various quantization processes, significantly improving performance and reducing resource requirements, making it suitable for deployment on various hardware.

Natural Language ProcessingGguf

A fine-tuned version of the NousResearch/Llama-3.2-1B model on the ultrachat_200k dataset, focusing on dialogue task optimization.

Natural Language ProcessingTransformers

Copus-2x8B is a Mixture of Experts model based on the Llama-3-8B architecture, combining fine-tuned versions of dreamgen/opus-v1.2-llama-3-8b and NousResearch/Meta-Llama-3-8B-Instruct.

Natural Language ProcessingTransformers