A Stable Diffusion model fine-tuned on RTX ray-traced Minecraft game screenshots, capable of generating blocky world-style images with ray tracing effects

Computer VisionDiffusers

Plan2Align is a reward model designed for test-time translation tasks, supporting translation quality evaluation from Chinese to English, German, and Russian.

Natural Language ProcessingSafetensorsMultiple Languages

A text classification model fine-tuned based on distilbert-base-uncased, trained for specific tasks.

Natural Language ProcessingTransformers

A mental health counseling dialogue model fine-tuned based on LLaMA-3.2-1B, capable of running on CPU and low-memory devices

Natural Language ProcessingSafetensors

This reward model scored 92.6 on reward-bench and was fine-tuned using the decontaminated Skywork preference dataset v0.2 based on the GRM-Llama3.1-8B-sftreg model.

Natural Language ProcessingSafetensors

A high-performance 2B parameter reward model fine-tuned based on GRM-Gemma2-2B-sftreg, which performs excellently in reward benchmark tests and surpasses multiple 8B models

Natural Language ProcessingSafetensors

A 3B-parameter reward model based on the Llama3 architecture, achieving a score of 90.9 in the reward-bench evaluation, outperforming multiple 8B reward models

Natural Language ProcessingSafetensors

LoRA diffusion model based on the FLUX framework, designed specifically for virtual try-on and fashion e-commerce scenarios of Ray-Ban Meta smart glasses

Computer VisionDiffusers

A scoring model based on Gemma-2b-it, trained with BT loss function, suitable for finding high-quality small scoring models for large language models

Natural Language ProcessingTransformers

A GPT2 large model trained on the Anthropic/hh-rlhf helpfulness dataset, specifically designed for helpful response detection or RLHF (Reinforcement Learning from Human Feedback).

Natural Language ProcessingTransformers

A large GPT2 model trained on the Anthropic/hh - rlhf harmless dataset, specifically for harmful response detection or reinforcement learning from human feedback (RLHF).

Natural Language ProcessingTransformers

This model is trained on the jnlpba dataset, fine-tuned based on the pre-trained PubMed version of RoBERTa, specifically designed to identify biomedical entities such as genes, DNA, RNA, and proteins

Natural Language ProcessingTransformersMultiple Languages

Named entity recognition model trained on NCBI Disease dataset and BC5CDR dataset, specialized in identifying disease entities in biomedical literature

Natural Language ProcessingTransformersMultiple Languages

This model is used to automatically add punctuation marks to unpunctuated classical Chinese texts, supporting over twenty types of punctuation.

Natural Language ProcessingTransformersMultiple Languages

A translation model that converts modern Chinese text into classical Chinese expressions automatically.

Natural Language ProcessingTransformersChinese

This model is used to translate Classical Chinese (Ancient Text) into Modern Chinese, supporting both punctuated and unpunctuated text input.

Natural Language ProcessingTransformersChinese