Models

BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder.

BAAI general embedding (Base) model that transforms any given text into a 768-dimensional vector

BAAI general embedding (Large) model that transforms any given text into a 1024-dimensional vector

Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.

BAAI general embedding (Small) model that transforms any given text into a 384-dimensional vector

Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can use it to re-rank retrieved documents.

Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language.

Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language.

DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder weights.

DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks.

Detection Transformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images).

Distilled BERT model that was finetuned on SST-2 for sentiment classification

DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate quantization method.

Stable Diffusion model that has been fine-tuned to be better at photorealism without sacrificing range.