This project provides a text generation model fine-tuned based on the Microsoft Phi-3.5-mini-instruct model, which has been converted to the GGUF format and is suitable for the llama.cpp inference framework. The model was fine-tuned on the philschmid/guanaco-sharegpt-style dataset, optimizing its instruction-following and dialogue capabilities, and is suitable for efficient text generation tasks in resource-constrained environments.

Natural Language ProcessingGguf

This is a quantized version of the Microsoft Fara-7B model, optimized using the imatrix technology of llama.cpp. The model supports multiple quantization levels, from high-precision bf16 to extremely low-precision IQ2_M, meeting the needs of different hardware configurations and performance requirements.

Natural Language ProcessingGguf

Fara-7B is an efficient small language model specially designed by Microsoft for computer usage scenarios. It has only 7 billion parameters and performs excellently in advanced user tasks such as web operations, competing with larger agent systems.

MultimodalGguf

Fara-7B is a small language model developed by Microsoft Research, specifically designed for computer usage scenarios. It has only 7 billion parameters and achieves excellent performance among models of the same scale. It can perform computer interaction tasks such as web automation and multimodal understanding.

MultimodalTransformersEnglish

This is a quantized version of the Microsoft UserLM-8b model, using the imatrix quantization technology of llama.cpp. It can significantly reduce memory usage and improve inference speed while maintaining model performance. It supports multiple quantization levels, from high quality to extreme compression, suitable for different hardware environments.

Natural Language ProcessingGguf

UserLM-8b-Q8_0-GGUF is a GGUF format version converted from the Microsoft UserLM-8b model, a large language model specifically optimized for user conversation scenarios. This model uses 8-bit quantization technology, significantly reducing the model size while maintaining performance, making it easy to deploy and run on various hardware.

Natural Language ProcessingGgufEnglish

This model is a fine-tuned version of microsoft/speech-t5, specifically optimized for Latin. It was trained using 67 hours of Latin audio data from the Vox Classica dataset and can achieve high-quality Latin text-to-speech conversion.

Audio ProcessingSafetensorsOther

A three-stage training GRPO inference test model based on the microsoft/phi-4 (14B) base model, fine-tuned through the SFT→RLHF→SFT process, with excellent multi-step reasoning ability

Natural Language ProcessingTransformersMultiple Languages

vibevoice-gguf is a text-to-speech system based on the Microsoft VibeVoice-1.5B model. It runs through the gguf-connector and can convert text into natural speech. It supports voice cloning and multi-speaker voice generation.

Audio ProcessingGguf

A quantized version of the Microsoft NextCoder - 32B model, which uses the llama.cpp tool to quantize the original model for more efficient operation under different hardware conditions.

Natural Language ProcessingGgufMultiple Languages

A speech synthesis model fine-tuned based on microsoft/speecht5_tts, suitable for speech synthesis tasks.

Audio ProcessingTransformers

The quantized version of NatureLM-8x7B-Inst, aiming to make knowledge accessible to everyone.

Natural Language ProcessingGguf

Blake-XTM Arc 3B (V1) is a large instruction language model with 3B parameters, fine-tuned based on microsoft/phi-2, supporting text generation, reasoning, and tool invocation.

Natural Language ProcessingGgufEnglish

GUI-Actor-2B is a vision-language model based on Qwen2-VL-2B, specifically designed for graphical user interface (GUI) positioning tasks. By adding an attention-based action head and fine-tuning, it performs well in multiple GUI positioning benchmark tests.

MultimodalTransformers

GUI-Actor-7B is a vision-language model developed based on Qwen2-VL-7B-Instruct, focusing on graphical user interface (GUI) agent tasks and providing a coordinate-free visual grounding solution.

MultimodalTransformers

A Khmer name recognition model fine-tuned based on Microsoft TrOCR, specifically designed for optical character recognition tasks of Khmer scripts.

Computer VisionTransformersOther

An image-to-text model fine-tuned based on Microsoft Florence-2 foundation model, supporting Swedish and English, specializing in historical handwritten text recognition and optical character recognition.

MultimodalSafetensorsMultiple Languages

Humains-Junior is an AI assistant trained by Humains.com based on the Microsoft Phi-3.5-mini-instruct model, specifically optimized for the customer service scenario. This model is fine-tuned using 300 million tokens, with strict instruction-following ability, reduced hallucination, and powerful function call ability, and it implements identity awareness.

Natural Language ProcessingTransformersEnglish

This is a Vietnamese text-to-speech model fine-tuned based on Microsoft SpeechT5, which can convert Vietnamese text into natural speech and supports two types of voice outputs, male and female.

Audio ProcessingSafetensorsOther

An MLX 4-bit quantized version converted from the microsoft/Phi-4-reasoning-plus model, optimized for Apple Silicon, with high-performance in multiple fields such as natural language processing, mathematical reasoning, code generation, and dialogue.

Natural Language ProcessingMlxMultiple Languages