An inference-optimized model fine-tuned based on Falcon3-Mamba-7B-Instruct, utilizing the Mamba architecture for efficient inference

Natural Language ProcessingTransformers

This is a quantized version of the Falcon3-10B-Instruct-abliterated model, which is quantized using the llama.cpp tool with the imatrix option. It provides model files with various quantization levels, suitable for different hardware environments and application scenarios.

Natural Language ProcessingGgufMultiple Languages

This is the GGUF quantization version of the Falcon3-3B-Base model, using the llama.cpp b4381 version for imatrix quantization processing. This version offers multiple quantization levels, from high quality to low memory usage, suitable for running on different hardware configurations.

Natural Language ProcessingGgufMultiple Languages

Falcon3 7B-IT and 7B-IT Mixture of Experts model with 13.4 billion parameters, supporting English, French, Spanish, and Portuguese, with a context length of up to 32K.

Natural Language ProcessingSafetensorsEnglish

Falcon3-10B-Instruct is an open-source foundational model from the Falcon3 series, featuring 10 billion parameters, specializing in high-quality instruction-following tasks, supporting multilingual processing with a context length of up to 32K tokens.

Natural Language ProcessingGguf

A quantized version of Falcon3-7B-Instruct, optimized using the imatrix technology of llama.cpp, offering multiple quantization levels and supporting multilingual dialogue tasks in English, French, Spanish, and Portuguese.

Natural Language ProcessingGgufMultiple Languages