This model is a large language model fine-tuned on a specific dataset based on meta-llama/Llama-3.1-70B-Instruct. It is specifically designed for text generation tasks and achieved a loss value of 0.6542 on the evaluation set.

Natural Language ProcessingPeft

Sunflower-14B is a multilingual large language model developed by Sunbird AI, specifically designed for Ugandan languages. This model is built on the Qwen 3-14B architecture and supports translation and text generation tasks for 31 Ugandan languages and English, performing excellently in multiple evaluations.

Natural Language ProcessingTransformersMultiple Languages

This model is a large language model fine-tuned on a specific dataset based on Qwen/Qwen3-8B. It achieved a loss value of 0.2248 on the evaluation set and has improved natural language processing capabilities.

Natural Language ProcessingTransformers

This is a large language model fine-tuned based on Qwen2.5-7B-Instruct. It was trained on the C2_re_100k_tag5_cleaned_hermes_toolv6_dethink_replacedv1 dataset and achieved a loss value of 0.2549 on the evaluation set. It has optimized dialogue and tool usage capabilities.

Natural Language ProcessingTransformers

This model is a large language model fine-tuned on the 2and3_apps_30k_v6 dataset based on Qwen/Qwen2.5-7B-Instruct. It achieved a loss value of 0.1593 on the evaluation set, showing good performance.

Natural Language ProcessingTransformers

DeepSeek-GRM-16B is a generative reward model based on Self-Principled Critique Tuning (SPCT), which can generate a transparent 'Principle → Critique → Score' evaluation process for query-responses and can be used in tasks such as reinforcement learning, evaluation, and data collection of large language models.

Natural Language ProcessingTransformersMultiple Languages

OpenCodeReasoning-Nemotron-1.1-7B is a large language model with 7 billion parameters developed based on Qwen2.5-7B-Instruct. It is specifically optimized through post-training for code generation and reasoning tasks. This model supports a context length of 64k tokens and performs excellently in competitive programming tasks, achieving a one-time pass rate of 55.5% in the LiveCodeBench evaluation.

Natural Language ProcessingTransformersMultiple Languages

CompassJudger-2 is a series of brand-new general evaluation models designed to overcome the problems of narrow professionalism and limited robustness in existing large language model evaluation solutions.

Natural Language ProcessingTransformers

Llama Guard 4 is a native multimodal safety classifier with 12 billion parameters, jointly trained on text and multiple images for content safety evaluation of large language model inputs and outputs.

MultimodalTransformersEnglish

VisualPRM-8B-v1.1 is an advanced multimodal process reward model with 8 billion parameters, which enhances the reasoning ability of large multimodal language models through the Best-of-N evaluation strategy.

MultimodalTransformersmultilingual

YugoGPT-Florida is a large language model based on Serbian, excelling in multiple evaluation benchmarks.

Natural Language ProcessingGgufOther

LLaVAction is a multimodal large language model evaluation and training framework for action recognition, based on the Qwen2 language model architecture, supporting first-person perspective video understanding.

MultimodalTransformersEnglish

STILL-3-TOOL-32B is a large language model that utilizes Python code to assist in the reasoning process, achieving an accuracy rate of 81.70% in the AIME 2024 evaluation.

Natural Language ProcessingTransformers

Root Judge is a powerful medium-sized large language model designed for reliable and customizable LLM system evaluation. Fine-tuned based on Llama-3.3-70B-Instruct, it excels in pairwise preference judgment and multi-round instruction following tasks with source references.

Natural Language ProcessingSafetensorsEnglish

MMIE is an evaluation benchmark specifically designed for large vision-language models, featuring an automated scoring system to test multimodal interleaved comprehension capabilities.

MultimodalSafetensorsEnglish

Flow Judge v0.1 is a lightweight but powerful model with 3.8 billion parameters, which can perform customized evaluations on large language model (LLM) systems in multiple fields.

Natural Language ProcessingTransformersEnglish

A Basque - Spanish machine translation model jointly developed by the HiTZ Research Center and the IXA Research Group of the University of the Basque Country. It is trained on a large number of parallel datasets and performs well on multiple evaluation datasets.

Natural Language ProcessingTransformersMultiple Languages

M3D is a 3D medical image analysis technology based on multimodal large language models, including the M3D-Data dataset, M3D-LaMed model, and M3D-Bench evaluation benchmark.

MultimodalTransformers

MiniCPM is an edge-side large language model series jointly developed by FaceWall Intelligence and Tsinghua University's Natural Language Processing Laboratory. The core model contains only 1.2 billion non-embedding parameters and outperforms larger open-source models in multiple evaluations.

Natural Language ProcessingTransformersMultiple Languages

Agent-FLAN-7b is a large language model based on the Llama2-7b model. It is obtained through mixed fine-tuning on the AgentInstruct, Toolbench, and ShareGPT datasets using the data generation pipeline proposed in the Agent-FLAN paper. This model is specifically optimized for agent tasks and tool usage capabilities, and it performs excellently on various agent evaluation datasets, showing a 3.5% improvement compared to the previous best work.

Natural Language ProcessingTransformers