OpenMMReasoner is a completely transparent two-stage multimodal reasoning solution, trained using supervised fine-tuning (SFT) and reinforcement learning (RL). A cold-start dataset of 874K samples was constructed in the SFT stage, and the RL stage used 74K samples to further enhance its capabilities, showing excellent performance in multimodal reasoning benchmark tests.

MultimodalTransformers

OpenMMReasoner is a fully transparent two-stage multimodal reasoning solution that covers supervised fine-tuning (SFT) and reinforcement learning (RL). By carefully constructing high-quality datasets, this solution surpasses powerful baseline models in multiple multimodal reasoning benchmark tests, laying a solid empirical foundation for future large-scale multimodal reasoning research.

MultimodalTransformers

Olmo 3 32B Think SFT is an autoregressive language model based on the Transformer architecture, which performs excellently in long-chain thought reasoning and is particularly good at handling complex reasoning tasks such as mathematics and coding. This model was pre-trained on the Dolma 3 dataset and supervised fine-tuned on the Dolci dataset.

Natural Language ProcessingTransformersEnglish

Apriel-1.5-15b-Thinker is a multimodal reasoning model in the ServiceNow Apriel SLM series, with 15 billion parameters. It can compete with models 10 times its size in text and image reasoning tasks. This model achieves excellent reasoning ability through a mid-term training scheme and can reach SOTA performance without image SFT training or reinforcement learning.

MultimodalTransformers

Mellum-4b-dpo-all is a large language model with 4 billion parameters developed by JetBrains, specifically designed for code generation and understanding. After three stages of training: pre - training, SFT, and Direct Preference Optimization (DPO), it can generate high - quality and readable code, supporting multiple programming languages.

Natural Language ProcessingTransformersOther

A lightweight medical fine-tuned model based on Arcee's AFM-4.5B, optimized using a three-stage training method (SFT→DPO→GRPO-CoT), specifically designed for medical education and research scenarios.

Natural Language ProcessingTransformersMultiple Languages

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

MiMo is a series of large language models trained from scratch by Xiaomi specifically for inference tasks. Through optimizing pre-training and post-training strategies, it demonstrates excellent performance in mathematical and code reasoning tasks. The project has open-sourced multiple versions with a 7B parameter scale, including the base model, SFT model, and RL model.

Natural Language ProcessingTransformers

MedGemma-GRPO is a fine-tuned version of the MEDGemma model, specifically designed for clinical case reasoning tasks. This model combines supervised fine-tuning (SFT) and group relative policy optimization (GRPO) to guide the model to follow logical diagnostic paths. It is trained on a synthetic medical case dataset and is particularly suitable for diagnostic reasoning of complex cardiovascular, thrombotic, and autoimmune diseases.

Natural Language ProcessingTransformersEnglish

This is the static quantization version of the Veri - Code/ReForm - SFT - 1.5B model, optimized for tasks such as code generation, reinforcement learning, and formal verification. It offers multiple quantization type options and significantly improves inference efficiency.

Natural Language ProcessingTransformersEnglish

This is the static quantized version of the Veri-Code/ReForm-SFT-14B model, providing GGUF files in multiple quantization formats, suitable for fields such as code generation and reinforcement learning. The model is optimized to run efficiently under different hardware configurations.

Natural Language ProcessingTransformersEnglish

AceInstruct-1.5B is an advanced SFT model for coding, mathematics, and general tasks. It is fine-tuned based on Qwen2.5-Base, and its performance is comparable to that of Qwen2.5-Instruct.

Natural Language ProcessingGgufMultiple Languages

Param 1 is an English-Hindi bilingual language model launched by BharatGen, with 2.9 billion parameters. The model is trained from scratch, supports English and Hindi, and has undergone early supervised fine-tuning (SFT), which can serve as a basis for downstream tasks, security testing, and customization.

Natural Language ProcessingSafetensorsMultiple Languages

ReasonGen-R1 is a text-to-image model trained on image prompts and reasoning basis datasets through supervised fine-tuning (SFT), with the explicit 'thinking' ability based on text.

MultimodalTransformers

ReasonGen-R1 is an autoregressive image generation model that integrates chain-of-thought reasoning. It enhances the logic and quality of image generation through SFT and RL.

MultimodalTransformers

This is a 70B-parameter large language model based on Llama 3.3, fine-tuned with SFT+DPO, specializing in character-driven dialogues and creative content generation

Natural Language ProcessingTransformers

A supervised fine-tuning (SFT) model based on the Transformers library, designed to optimize language model performance

Natural Language ProcessingTransformers

This is an experimental small reasoning model designed to run on 8GiB consumer-grade GPUs with general inference capabilities. Through supervised fine-tuning (SFT) and high-quality reasoning trajectory training, the model can generalize its reasoning abilities to multiple tasks.

Natural Language ProcessingGguf

MiMo-7B is a language model series launched by Xiaomi, specifically designed for reasoning tasks, including base models, SFT models, and RL models, excelling in mathematical and code reasoning tasks.

Natural Language ProcessingTransformers

OLMo 2 1B SFT is a supervised fine-tuned version of the OLMo-2-0425-1B model, trained on the Tulu 3 dataset, designed to achieve state-of-the-art performance across multiple tasks.

Natural Language ProcessingTransformersEnglish