PyLate is a tool library focused on sentence similarity calculation and information retrieval. It can perform efficient information retrieval tasks on multiple datasets, providing strong support for research and applications in related fields. This model supports 8 languages and performs excellently in multiple benchmark tests.

Natural Language ProcessingSafetensorsMultiple Languages

LFM2-VL-3B is a multimodal vision-language model developed by Liquid AI, built on the LFM2 backbone architecture. It has powerful visual understanding and reasoning capabilities, especially excelling in fine-grained perception tasks. This model can efficiently process text and image inputs and supports native image processing with a resolution of up to 512×512.

MultimodalTransformersMultiple Languages

This is a quantized version of the afkfatih/LFM2-8B-A1B-TR model, offering various GGUF quantization formats. The model is a multilingual large language model with 8 billion parameters, specifically optimized for the Turkish language and supporting 9 languages including English, Chinese, and Arabic.

Natural Language ProcessingTransformersMultiple Languages

LFM2-8B-A1B-qx86-hi-mlx is an efficient inference model based on the MLX format, converted from LiquidAI/LFM2-8B-A1B. This model adopts a mixture-of-experts architecture and demonstrates卓越的 efficiency in inference tasks. It is particularly擅长 at complex logical reasoning tasks and supports multilingual processing.

Natural Language ProcessingMlxMultiple Languages

This is an 8-bit quantized version converted from the LiquidAI/LFM2-8B-A1B model, optimized for the Apple MLX framework. This model is a mixture-of-experts model with 8B parameters, supporting multilingual text generation tasks.

Natural Language ProcessingMlxMultiple Languages

LFM2-8B-A1B is an 8-bit quantized MLX build version optimized for Apple Silicon chips, adopting the Mixture of Experts (MoE) architecture. It has approximately 8 billion total parameters, with about 1 billion parameters activated per token, and supports fast inference on the device side.

Natural Language ProcessingMlxEnglish

Tiny-Purr-350M is a conversational model fine-tuned based on LiquidAI/LFM2-350M. It is trained on the Tiny-Purr-2 dataset and has the ability to provide casual, friendly, and cat-themed conversational responses, supporting both Chinese and English.

Natural Language ProcessingPeftMultiple Languages

This is the GGUF quantized version of LiquidAI's LFM2-1.2B-RAG model, specifically optimized for Retrieval Augmented Generation (RAG) tasks. The model has undergone various quantization processes, offering multiple quantization levels from bf16 to Q2_K, suitable for different hardware conditions and performance requirements.

Natural Language ProcessingGguf

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment. It sets a new standard in terms of quality, speed, and memory efficiency. This model adopts an innovative hybrid Liquid architecture with multiplicative gates and short convolutions, supporting multilingual processing.

Natural Language ProcessingTransformersMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment. This model sets a new standard in terms of quality, speed, and memory efficiency, and is particularly suitable for running in resource-constrained environments.

Natural Language ProcessingGgufMultiple Languages

This is a statically quantized version of the LiquidAI/LFM2-350M-ENJP-MT model, supporting bidirectional translation tasks between English and Japanese. It is optimized for edge computing scenarios and offers various quantization options to meet different hardware requirements.

Natural Language ProcessingTransformersMultiple Languages

LFM2-Audio-1.5B is the first end-to-end audio foundation model launched by Liquid AI, designed specifically for low-latency and real-time conversations. With only 1.5 billion parameters, this model can achieve seamless conversational interactions, and its capabilities can rival those of models with much larger parameter scales.

MultimodalSafetensorsEnglish

Luth-LFM2-700M is a French fine-tuned version based on Liquid AI's LFM2-700M model. This model is trained on the Luth-SFT dataset, significantly improving French instruction following, mathematical, and general knowledge reasoning abilities while maintaining the original English capabilities.

Natural Language ProcessingTransformersMultiple Languages

This is the quantized version of LiquidAI's LFM2-VL-1.6B model, which uses llama.cpp for imatrix quantization processing. It offers multiple quantization levels and can efficiently run vision-language models under different hardware conditions.

MultimodalGguf

The Japanese Receipt Vision-Language Model lfm2-450M is a vision-language model specifically designed for understanding and processing Japanese receipts. It is built on LiquidAI's LFM2-VL-450M base model, capable of analyzing receipt images, extracting structured information, answering questions about the receipt content, and providing detailed descriptions in Japanese and English.

MultimodalTensorboardMultiple Languages

Luth-LFM2-350M is a French-optimized language model developed in collaboration with Liquid AI. It is fine-tuned on the Luth-SFT dataset based on LFM2-350M for French. This model significantly improves French instruction following, mathematical reasoning, and common-sense question-answering abilities while maintaining English proficiency.

Natural Language ProcessingTransformersMultiple Languages

LFM2-1.2B is a multilingual text generation model launched by LiquidAI, supporting multiple languages such as English, Chinese, and Arabic, providing strong support for scenarios like text creation. This model is optimized by MLX and is particularly adapted to Apple Silicon chips.

Natural Language ProcessingTransformersMultiple Languages

LFM2-1.2B is a multilingual text generation model with a parameter scale of 1.2B launched by LiquidAI, optimized for Apple Silicon chips.

Natural Language ProcessingTransformersMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in terms of quality, speed, and memory efficiency.

Natural Language ProcessingGgufMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in quality, speed, and memory efficiency.

Natural Language ProcessingGgufMultiple Languages