As traduções são geradas por tradução automática. Em caso de conflito entre o conteúdo da tradução e da versão original em inglês, a versão em inglês prevalecerá. # Modelos de base disponíveis A Amazon SageMaker JumpStart oferece modelos básicos de última geração, incorporados, disponíveis ao público e proprietários, para personalizar e integrar aos seus fluxos de trabalho generativos de IA. Para listar todos os modelos de JumpStart fundação disponíveis: ``` import boto3 sagemaker_client = boto3.client("sagemaker", region_name="us-west-2") # List all available models in the SageMakerPublicHub all_models = [] next_token = None while True: params = {"HubName": "SageMakerPublicHub", "HubContentType": "Model"} if next_token: params["NextToken"] = next_token response = sagemaker_client.list_hub_contents(**params) all_models.extend(response["HubContentSummaries"]) next_token = response.get("NextToken") if not next_token: break print(f"Total models available: {len(all_models)}") for model in all_models[:5]: print(model["HubContentName"], model["HubContentVersion"]) ``` Para obter tipos de instância compatíveis e outros metadados para um modelo específico: ``` import json import boto3 sagemaker_client = boto3.client("sagemaker", region_name="us-west-2") model_id = "meta-textgeneration-llama-3-3-70b-instruct" response = sagemaker_client.describe_hub_content( HubName="SageMakerPublicHub", HubContentType="Model", HubContentName=model_id ) # Parse the model metadata model_doc = json.loads(response["HubContentDocument"]) print(f"Supported instances: {model_doc['SupportedInferenceInstanceTypes']}") print(f"Default instance: {model_doc['DefaultInferenceInstanceType']}") ``` As tabelas a seguir listam os modelos disponíveis com suas licenças e tipos de instância de inferência compatíveis a partir de 30 de abril de 2026. Para obter as informações mais atuais, use os exemplos de API acima ou consulte o hub de modelos no SageMaker Studio. ------ #### [ Open-Weight Models (417) ] Open-weight os modelos básicos são modelos disponíveis publicamente de fornecedores como Meta, Google, Mistral AI e outros. Você pode implantar, ajustar e personalizar esses modelos para seu caso de uso. Para começar a usar um desses modelos, consulte [JumpStart uso do modelo básico](jumpstart-foundation-models-use.md) ou explore um dos disponíveis[Cadernos de exemplo](jumpstart-foundation-models-example-notebooks.md). Em um determinado notebook de exemplo, tente trocar o ID do modelo para experimentar modelos diferentes dentro da mesma família de modelos. Para obter mais informações sobre IDs de modelo e recursos sobre a implantação de modelos JumpStart básicos disponíveis publicamente com o SageMaker Python SDK, consulte. [Use modelos de base com o SageMaker Python SDK](jumpstart-foundation-models-use-python-sdk.md) | Fornecedor | Nome do modelo | ID do modelo | Tarefa | Licença | Fine-tunable | Tipos de instância de inferência compatíveis | | --- | --- | --- | --- | --- | --- | --- | | 01-AI | Yi-1.5-34B | huggingface-llm-yi-1-5-34b | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | 01-AI | Yi-1.5-9B | huggingface-llm-yi-1-5-9b | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Ahxt | Lite Llama 460M 1T | huggingface-llm-ahxt-litellama-460m-1t | Geração de texto | mit | Não | ml.g5.2xlarge | | Ai-Forever | Multilingual GPT | huggingface-llm-ai-forever-mgpt | Geração de texto | apache-2.0 | Não | ml.g5.2xlarge | | Aisingapura | Llama3 8B v2.1 Instruct SEA-Lion | huggingface-llm-llama3-8b-sealionv21-instruct | Geração de texto | lhama 3 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.p4d.24xlarge, ml.p5.48xlarge grande | | Aisingapura | SEA-LION 3B | huggingface-llm-sealion-3b | Geração de texto | mit | Não | ml.g4dn.2xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.p3.8xlarge | | Aisingapura | SEA-LION 7B | huggingface-llm-sealion-7b | Geração de texto | mit | Não | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Aisingapura | SEA-LION Instrução 7B | huggingface-llm-sealion-7b-instruct | Geração de texto | mit | Não | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Alibaba-Nlp | Alibaba-NLP obter- Qwen2-7B-instruct | huggingface-textembedding-gte-qwen2-7b-instruct | Incorporação de texto | Apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge | | Allenai | Olmo-3-7B-Instruct | huggingface-textgeneration-olmo-3-7b-instruct | Geração de texto | apache-2.0 | Não | ml.g6e.24xlarge | | Amazon | Chronos 2 | pytorch-forecasting-chronos-2 | Previsão de séries temporais | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.xlarge, ml.g6.2xlarge, ml.g6e.2xlarge, ml.g6e.2xlarge p.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.xlarge | | Amazon | Falcon Lite | huggingface-llm-amazon-falconlite | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | Amazon | Falcon Lite 2 | huggingface-llm-amazon-falconlite2 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | Amazon | Mistral Lite | huggingface-llm-amazon-mistrallite | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Autógluon | Chronos-Bolt (Base) | autogluon-forecasting-chronos-bolt-base | Previsão de séries temporais | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.4xlarge, ml.m5.4xlarge, ml.m5.4xlarge x grande, ml.p 3,2 x grande | | Autógluon | Chronos-Bolt (Pequeno) | autogluon-forecasting-chronos-bolt-small | Previsão de séries temporais | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.4xlarge, ml.m5.4xlarge, ml.m5.4xlarge x grande, ml.p 3,2 x grande | | Autógluon | Chronos-T5 (Base) | autogluon-forecasting-chronos-t5-base | Previsão de séries temporais | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Autógluon | Chronos-T5 (Grande) | autogluon-forecasting-chronos-t5-large | Previsão de séries temporais | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Autógluon | Chronos-T5 (Pequeno) | autogluon-forecasting-chronos-t5-small | Previsão de séries temporais | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Baai | BAAI bge-base-pt-v1.5 | huggingface-textembedding-bge-base-en-v1-5 | Incorporação de texto | mit | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge | | Baai | BGE Base En | huggingface-sentencesimilarity-bge-base-en | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Baai | BGE Base En V1.5 | huggingface-sentencesimilarity-bge-base-en-v1-5 | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Baai | Caneta grande BGE | huggingface-sentencesimilarity-bge-large-en | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Baai | Extremidade grande BGE V1.5 | huggingface-sentencesimilarity-bge-large-en-v1-5 | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Baai | GRANDE M3 | huggingface-sentencesimilarity-bge-m3 | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Baai | BGE Small End | huggingface-sentencesimilarity-bge-small-en | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Baai | BGE Small End V1.5 | huggingface-sentencesimilarity-bge-small-en-v1-5 | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Berkeley-Nest | Starling LM 7B alfa | huggingface-llm-berkeley-nest-starling-lm-7b-alpha | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge | | Bharatgenai | Param2-17B-A2.4B-Thinking | huggingface-llm-param2-17b-a2-4b-thinking | Geração de texto | | Não | ml.g7e.2xlarge, ml.g7e.4xlarge, ml.g7e.8xlarge | | Código grande | StarCoder | huggingface-llm-starcoder | Geração de texto | código grande - openrail-m | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Código grande | StarCoderBase | huggingface-llm-starcoderbase | Geração de texto | código grande - openrail-m | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Grande ciência | Bloom 1b1 | huggingface-textgeneration-bloom-1b1 | Geração de texto | bigscience-bloom-rail-1.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Grande ciência | Bloom 3B | huggingface-textgeneration1-bloom-3b | Geração de texto | bigscience-bloom-rail-1.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Grande ciência | Bloom 7B1 | huggingface-textgeneration1-bloom-7b1 | Geração de texto | bigscience-bloom-rail-1.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Grande ciência | Bloomz 1b7 | huggingface-textgeneration-bloomz-1b7 | Geração de texto | bigscience-bloom-rail-1.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Grande ciência | BloomZ 7B1 FP16 | huggingface-textgeneration1-bloomz-7b1-fp16 | Geração de texto | bigscience-bloom-rail-1.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Bingsu | Bingsu, minha difusão estável coreana v1 5 | huggingface-txt2img-bingsu-my-korean-stable-diffusion-v1-5 | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.2xlarge, ml.g4dn.xlarge, ml.p3.2xlarge | | Black-Forest-Labs | Laboratórios da Floresta Negra FLUX.1 [rápido] | huggingface-txt2img-black-forest-labs-flux-1-schnell | Text-to-Image | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Cálculos cognitivos | Dolphin 2.2.1 Mistral 7B | huggingface-llm-dolphin-2-2-1-mistral-7b | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge | | Cálculos cognitivos | Dolphin 2.5 Mixtral 8 7B | huggingface-llm-dolphin-2-5-mixtral-8x7b | Geração de texto | apache-2.0 | Não | ml.g5.48xlarge | | Cálculos cognitivos | Dolphin 2.7 Mixtral 8 7B | huggingface-llm-dolphin-2-7-mixtral-8x7b | Geração de texto | apache-2.0 | Não | ml.g5.48xlarge | | Cálculos cognitivos | Dolphin 2.9 Llama 3 8b | huggingface-llm-cognitive-dolphin-29-llama3-8b | Geração de texto | outro | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Coerência para IA | Aya 101 | huggingface-llm-aya-101 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Cross-Encoder | Codificador cruzado Nli Deberta Base | huggingface-zstc-cross-encoder-nli-deberta-base | Zero-Shot Classificação | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Cross-Encoder | Codificador cruzado Nli Distilroberta Base | huggingface-zstc-cross-encoder-nli-distilroberta-base | Zero-Shot Classificação | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Cross-Encoder | Codificador cruzado Nli miniLM2 L6 H768 | huggingface-zstc-cross-encoder-nli-minilm2-l6-h768 | Zero-Shot Classificação | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Cross-Encoder | Codificador cruzado Nli Roberta Base | huggingface-zstc-cross-encoder-nli-roberta-base | Zero-Shot Classificação | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Agente cibernético | CyberAgentLM2-7B-Chat (CALM2-7B-Chat) | huggingface-llm-calm2-7b-chat-bf16 | Geração de texto | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge | | Databricks | DBRX Base | huggingface-llm-dbrx-base | Geração de texto | modelo aberto de tijolos de dados | Não | ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Databricks | DBRX Instruct | huggingface-llm-dbrx-instruct | Geração de texto | modelo aberto de tijolos de dados | Não | ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Databricks | Dolly V2 12b BF16 | huggingface-textgeneration-dolly-v2-12b-bf16 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Databricks | Dolly V2 3b BF16 | huggingface-textgeneration-dolly-v2-3b-bf16 | Geração de texto | apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Deepseek-Ai | DeepSeek-OCR | deepseek-vlm-deepseek-ocr | Image-Text-to-Text | mit | Não | ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.g6.16xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.16xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge, ml.p3.2xlarge | | Deepseek-Ai | DeepSeek-R1 | deepseek-llm-r1 | Geração de texto | mit | Não | ml.p5en.48xlarge | | Deepseek-Ai | DeepSeek-R1-0528 | deepseek-llm-r1-0528 | Geração de texto | mit | Não | ml.p5en.48xlarge | | Deepseek-Ai | DeepSeek-R1-Distill-Llama-70B | deepseek-llm-r1-distill-llama-70b | Geração de texto | mit | Sim | ml.g5,48xlarge, ml.g6,48xlarge, ml.p4d.24xlarge | | Deepseek-Ai | DeepSeek-R1-Distill-Llama-8B | deepseek-llm-r1-distill-llama-8b | Geração de texto | mit | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge | | Deepseek-Ai | DeepSeek-R1-Distill-Qwen-1.5B | deepseek-llm-r1-distill-qwen-1-5b | Geração de texto | mit | Sim | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge | | Deepseek-Ai | DeepSeek-R1-Distill-Qwen-14B | deepseek-llm-r1-distill-qwen-14b | Geração de texto | mit | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge | | Deepseek-Ai | DeepSeek-R1-Distill-Qwen-32B | deepseek-llm-r1-distill-qwen-32b | Geração de texto | mit | Sim | ml.g5,48xlarge, ml.g6,48xlarge, ml.p4d.24xlarge | | Deepseek-Ai | DeepSeek-R1-Distill-Qwen-7B | deepseek-llm-r1-distill-qwen-7b | Geração de texto | mit | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge | | Deepseek-Ai | DeepSeek-V3.1 | deepseek-llm-deepseek-v3-1 | Geração de texto | mit | Não | ml.p5en.48xlarge | | Deepseek-Ai | DeepSeek-V3.2 | deepseek-llm-deepseek-v3-2 | Geração de texto | mit | Não | ml.p5en.48xlarge | | Destilbert | Estojos base Distilbert | huggingface-tc-distilbert-base-cased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Estojos base Distilbert | huggingface-spc-distilbert-base-cased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Estojos base Distilbert | huggingface-eqa-distilbert-base-cased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Estojo multilíngue Distilbert Base | huggingface-tc-distilbert-base-multilingual-cased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Estojo multilíngue Distilbert Base | huggingface-spc-distilbert-base-multilingual-cased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Estojo multilíngue Distilbert Base | huggingface-eqa-distilbert-base-multilingual-cased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | DistilGPT 2 | huggingface-textgeneration-distilgpt2 | Geração de texto | apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Destilbert | DistilRoBERTa Base | huggingface-tc-distilroberta-base | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | DistilRoBERTa Base | huggingface-eqa-distilroberta-base | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Perguntas e respostas | huggingface-eqa-distilbert-base-uncased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Classificação de pares de frases | huggingface-spc-distilbert-base-uncased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Destilbert | Classificação de texto | huggingface-tc-distilbert-base-uncased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Elastic | Base Distilbert sem caixa | huggingface-ner-distilbert-base-uncased-finetuned-conll03-eng | Classificação de tokens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Elastic | Reconhecimento de entidades nomeadas | huggingface-ner-distilbert-base-cased-finetuned-conll03-english | Classificação de tokens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Elastic | Reconhecimento de entidades nomeadas | huggingface-ner-distilbert-base-cased-finetuned-conll03-eng | Classificação de tokens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Eleutherai | GPT-J 6B | huggingface-textgeneration1-gpt-j-6b | Geração de texto | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Eleutherai | GPT-Neo 125 M | huggingface-textgeneration1-gpt-neo-125m | Geração de texto | mit | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Eleutherai | gpt-neox-20b | huggingface-textgeneration2-gpt-neox-20b-fp16 | Geração de texto | Apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.p4d.24xlarge | | Eleutherai | Pythia 160m Deduped | huggingface-llm-eleutherai-pythia-160m-deduped | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge | | Eleutherai | Pythia 7m Deduped | huggingface-llm-eleutherai-pythia-70m-deduped | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge | | Elyza | ELYZA-japanese-Llama-2-13b-chat | huggingface-llm-elyza-japanese-llama-2-13b-chat | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Elyza | ELYZA-japanese-Llama-2-13b-fast-chat | huggingface-llm-elyza-japanese-llama-2-13b-fast-chat | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Elyza | ELYZA-japanese-Llama-2-7b-chat | huggingface-llm-elyza-japanese-llama-2-7b-chat-bf16 | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.xlarge | | Elyza | ELYZA-japanese-Llama-2-7b-fast-chat | huggingface-llm-elyza-japanese-llama-2-7b-fast-chat-bf16 | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.xlarge | | Emrecan | Allnli Tr com casca turca americana à base de berinjela | huggingface-zstc-emrecan-bert-base-turkish-cased-allnli-tr | Zero-Shot Classificação | mit | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook | Zero-Shot Classificação de texto | huggingface-zstc-facebook-bart-large-mnli | Zero-Shot Classificação | mit | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | Base Roberta | huggingface-tc-roberta-base | Classificação de texto | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | Base Roberta | huggingface-spc-roberta-base | Fill-Mask | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | Base Roberta | huggingface-eqa-roberta-base | Perguntas e respostas | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | Roberta Large | huggingface-tc-roberta-large | Classificação de texto | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | Roberta Large | huggingface-spc-roberta-large | Fill-Mask | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | Roberta Large | huggingface-eqa-roberta-large | Perguntas e respostas | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM CLM English-German | huggingface-tc-xlm-clm-ende-1024 | Classificação de texto | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM CLM English-German | huggingface-spc-xlm-clm-ende-1024 | Fill-Mask | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM 15 idiomas XNLI | huggingface-spc-xlm-mlm-xnli15-1024 | Fill-Mask | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM English-German | huggingface-tc-xlm-mlm-ende-1024 | Classificação de texto | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM English-German | huggingface-spc-xlm-mlm-ende-1024 | Fill-Mask | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM English-Romanian | huggingface-tc-xlm-mlm-enro-1024 | Classificação de texto | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM English-Romanian | huggingface-spc-xlm-mlm-enro-1024 | Fill-Mask | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM TLM 15 idiomas XNLI | huggingface-tc-xlm-mlm-tlm-xnli15-1024 | Classificação de texto | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Facebook AI | XLM MLM TLM 15 idiomas XNLI | huggingface-spc-xlm-mlm-tlm-xnli15-1024 | Fill-Mask | cc-by-nc-4.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Fictiverso | Modelo de difusão estável fictiverso BalloonArt | huggingface-txt2img-fictiverse-stable-diffusion-balloonart | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Fictiverso | Modelo microscópico de difusão estável fictiverso | huggingface-txt2img-fictiverse-stable-diffusion-micro-model | Text-to-Image | trilho aberto | Não | ml.g4dn.2xlarge, ml.g4dn.xlarge, ml.p3.2xlarge | | Fictiverso | Modelo de difusão estável fictiverso PaperCut | huggingface-txt2img-fictiverse-stable-diffusion-papercut-model | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.2xlarge, ml.g4dn.xlarge, ml.p3.2xlarge | | Fictiverso | Modelo de difusão estável fictiverso VoxelArt | huggingface-txt2img-fictiverse-stable-diffusion-voxelart-model | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Google | Arquivo grande do Bigbird Pegasus | huggingface-summarization-bigbird-pegasus-large-arxiv | Resumo de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google | Bigbird Pegasus Large Pubmed | huggingface-summarization-bigbird-pegasus-large-pubmed | Resumo de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google | Flan-T5 Base | huggingface-text2text-flan-t5-base | Text2Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Google | Flan-T5 Grande | huggingface-text2text-flan-t5-large | Text2Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Google | Flan-T5 Pequeno | huggingface-text2text-flan-t5-small | Text2Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Google | Flan-T5 XL | huggingface-text2text-flan-t5-xl | Text2Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Google | Flan-T5 XXL | huggingface-text2text-flan-t5-xxl | Text2Geração de texto | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Google | Gemma 2 27B | huggingface-llm-gemma-2-27b | Geração de texto | gema | Não | ml.g5.48xlarge, ml.p4d.24xlarge | | Google | Gemma 2 27B Instruir | huggingface-llm-gemma-2-27b-instruct | Geração de texto | gema | Não | ml.g5.48xlarge, ml.p4d.24xlarge | | Google | Gemma 2 2B | huggingface-llm-gemma-2-2b | Geração de texto | gema | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Google | Gemma 2 2B Instruir | huggingface-llm-gemma-2-2b-instruct | Geração de texto | gema | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Google | Gemma 2 9B | huggingface-llm-gemma-2-9b | Geração de texto | gema | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Google | Gemma 2 9B Instruir | huggingface-llm-gemma-2-9b-instruct | Geração de texto | gema | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Google | Gemma 2B Instruct | huggingface-llm-gemma-2b-instruct | Geração de texto | gema | Sim | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Google | Gemma 3 1B Instruir | huggingface-llm-gemma-3-1b-instruct | Geração de texto | gema | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Google | Gemma 3 27B Instruir | huggingface-vlm-gemma-3-27b-instruct | Image-Text-to-Text | gema | Não | ml.g5.48xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Google | Gemma 3 4B Instruir | huggingface-vlm-gemma-3-4b-instruct | Image-Text-to-Text | gema | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Google | gemma-2b | huggingface-llm-gemma-2b | Geração de texto | gema | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.g6.xlarge, ml.g6e.xlarge, ml.p3.2xlarge, ml.p4d.24xlarge | | Google | gemma-4-26b-a4b-it | huggingface-vlm-gemma-4-26b-a4b-it | Geração de texto | apache-2.0 | Não | ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Google | gemma-4-31b-it | huggingface-vlm-gemma-4-31b-it | Image-Text-to-Text | Apache-2.0 | Não | ml.g6.24xlarge | | Google | gemma-4-e4b-it | huggingface-vlm-gemma-4-e4b-it | Geração de texto | apache-2.0 | Não | ml.g6.12xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Google | gemma-7b | huggingface-llm-gemma-7b | Geração de texto | gema | Sim | ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Google | gemma-7b-bit | huggingface-llm-gemma-7b-instruct | Geração de texto | gema | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Google-Bert | Base BERT cased | huggingface-tc-bert-base-cased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Base BERT cased | huggingface-spc-bert-base-cased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Base BERT cased | huggingface-eqa-bert-base-cased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Estojo multilíngue Base BERT | huggingface-tc-bert-base-multilingual-cased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Estojo multilíngue Base BERT | huggingface-spc-bert-base-multilingual-cased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Estojo multilíngue Base BERT | huggingface-eqa-bert-base-multilingual-cased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT Base, multilíngue, sem caixa | huggingface-tc-bert-base-multilingual-uncased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT Base, multilíngue, sem caixa | huggingface-spc-bert-base-multilingual-uncased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT Base, multilíngue, sem caixa | huggingface-eqa-bert-base-multilingual-uncased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Base BERT uncased | huggingface-tc-bert-base-uncased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Base BERT uncased | huggingface-spc-bert-base-uncased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Base BERT uncased | huggingface-eqa-bert-base-uncased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT grande cased | huggingface-tc-bert-large-cased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT grande cased | huggingface-spc-bert-large-cased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT grande cased | huggingface-eqa-bert-large-cased | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Máscara de palavras inteiras BERT grande cased | huggingface-spc-bert-large-cased-whole-word-masking | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Máscara de palavras inteiras BERT grande cased | huggingface-eqa-bert-large-cased-whole-word-masking | Perguntas e respostas | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT grande uncased | huggingface-tc-bert-large-uncased | Classificação de texto | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | BERT grande uncased | huggingface-spc-bert-large-uncased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Máscara de palavras inteiras BERT grande uncased | huggingface-spc-bert-large-uncased-whole-word-masking | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-Bert | Máscara de enchimento | huggingface-fillmask-bert-base-uncased | Fill-Mask | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-T5 | Tradução de máquina | huggingface-translation-t5-small | Tradução | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-T5 | t5 Base en de | huggingface-translation-t5-base | Tradução | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Google-T5 | t5 Large en de | huggingface-translation-t5-large | Tradução | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Gradientes | Llama-3 8B Gradient Instruct 1048k | huggingface-llm-llama-3-8b-instruct-gradient | Geração de texto | lhama 3 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Gradientes | Llama-3 8B Gradient Instruct 262k | huggingface-llm-gradientai-llama-3-8B-instruct-262k | Geração de texto | lhama 3 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Helsinki-Nlp | Helsinque opus en es | huggingface-translation-opus-mt-en-es | Tradução | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Helsinki-Nlp | Helsinque opus en vi | huggingface-translation-opus-mt-en-vi | Tradução | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Helsinki-Nlp | Helsinque opus mul en | huggingface-translation-opus-mt-mul-en | Tradução | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Abraçando o rosto h4 | HuggingFaceZéfiro H4 orpo-141b- A35b-v0.1 | huggingface-llm-huggingfaceh4-zephyr-orpo-141b-a35b-v01 | Geração de texto | apache-2.0 | Não | ml.g5.48xlarge, ml.p4d.24xlarge | | Abraçando o rosto h4 | Star Chat Alpha | huggingface-llm-huggingfaceh4-starchat-alpha | Geração de texto | código grande - openrail-m | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | Abraçando o rosto h4 | Star Chat Beta | huggingface-llm-huggingfaceh4-starchat-beta | Geração de texto | código grande - openrail-m | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Abraçando o rosto h4 | Zephyr 7B Beta | huggingface-llm-huggingfaceh4-zephyr-7b-beta | Geração de texto | mit | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | IBM | Quality Controlled Paraphrase Generation | huggingface-text2text-qcpg-sentences | Text2Geração de texto | apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Idea-Ccnl | Difusão estável IDEA CCNL Taiyi 1B EN chinesa v0.1 | huggingface-txt2img-idea-ccnl-taiyi-1b-chinese-en-v01 | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Idea-Ccnl | Difusão estável IDEA CCNL Taiyi 1B chinesa v0.1 | huggingface-txt2img-idea-ccnl-taiyi-1b-chinese-v0-1 | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Infloat | Base E5 | huggingface-sentencesimilarity-e5-base | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Infloat | E5 Base V2 | huggingface-sentencesimilarity-e5-base-v2 | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Infloat | E5 Grande V2 | huggingface-sentencesimilarity-e5-large-v2 | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Infloat | Base E5 multilíngue | huggingface-sentencesimilarity-multilingual-e5-base | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Infloat | E5 grande multilíngue | huggingface-sentencesimilarity-multilingual-e5-large | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Langboat | Difusão de Langboat Guohua | huggingface-txt2img-langboat-guohua-diffusion | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.2xlarge, ml.g4dn.xlarge, ml.p3.2xlarge | | Luz eterna | Lighteternal Nli Xlm R Grego | huggingface-zstc-lighteternal-nli-xlm-r-greek | Zero-Shot Classificação | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Meta | Llama-2-7b-hf | meta-textgeneration-llama-2-7b | Geração de texto | lhama 2 | Sim | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g6.12xlarge, ml.g6e.xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama-3.1-70B-Instruct | meta-textgeneration-llama-3-1-70b-instruct | Geração de texto | lhama 3.1 | Sim | ml.g6e.48xlarge, ml.p5en.48xlarge | | Meta | Llama-3.1-8B-Instruct | meta-textgeneration-llama-3-1-8b-instruct | Geração de texto | lhama 3.1 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.p3.16xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama-3.2-1B | meta-textgeneration-llama-3-2-1b | Geração de texto | lhama 3.2 | Sim | ml.g4dn.12xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6e.2xlarge, ml.p3.16xlarge, ml.p4d.24xlarge | | Meta | Llama-3.2-1B-Instruct | meta-textgeneration-llama-3-2-1b-instruct | Geração de texto | lhama 3.2 | Sim | ml.g4dn.12xlarge, ml.g5.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama-3.2-3B | meta-textgeneration-llama-3-2-3b | Geração de texto | lhama 3.2 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p3.16xlarge, ml.p5en.48xlarge | | Meta | Llama-3.2-3B-Instruct | meta-textgeneration-llama-3-2-3b-instruct | Geração de texto | lhama 3.2 | Sim | ml.g5.24xlarge, ml.g6.24xlarge, ml.g6e.48xlarge, ml.p3.16xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama-Guard-3-1B | meta-textgeneration-llama-guard-3-1b | Geração de texto | lhama 3.2 | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.16xlarge e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge, ml.p4d.24xlarge | | Meta | Llama-Guard-3-8B | meta-textgeneration-llama-guard-3-8b | Geração de texto | lhama 3.1 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.p4d.24xlarge | | Meta | Code Llama 13B da Meta | meta-textgeneration-llama-codellama-13b | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.p4d.24xlarge | | Meta | Code Llama 13B Instruct da Meta | meta-textgeneration-llama-codellama-13b-instruct | Geração de texto | lhama 2 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.p4d.24xlarge | | Meta | Code Llama 13B Python da Meta | meta-textgeneration-llama-codellama-13b-python | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.p4d.24xlarge | | Meta | Code Llama 34B da Meta | meta-textgeneration-llama-codellama-34b | Geração de texto | lhama 2 | Sim | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Code Llama 34B Instruct da Meta | meta-textgeneration-llama-codellama-34b-instruct | Geração de texto | lhama 2 | Não | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Code Llama 34B Python da Meta | meta-textgeneration-llama-codellama-34b-python | Geração de texto | lhama 2 | Sim | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Code Llama 70B da Meta | meta-textgeneration-llama-codellama-70b | Geração de texto | lhama 2 | Sim | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Code Llama 70B Instruct da Meta | meta-textgeneration-llama-codellama-70b-instruct | Geração de texto | lhama 2 | Não | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Code Llama 70B Neuron da Meta | meta-textgenerationneuron-llama-codellama-70b | Geração de texto | lhama 2 | Não | ml.inf2.48xlarge | | Meta | Code Llama 70B Python da Meta | meta-textgeneration-llama-codellama-70b-python | Geração de texto | lhama 2 | Sim | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Code Llama 7B da Meta | meta-textgeneration-llama-codellama-7b | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.2xlarge, ml.p4d.24xlarge | | Meta | Code Llama 7B Instruct da Meta | meta-textgeneration-llama-codellama-7b-instruct | Geração de texto | lhama 2 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.g6.2xlarge, ml.p4d.24xlarge | | Meta | Code Llama 7B Neuron da Meta | meta-textgenerationneuron-llama-codellama-7b | Geração de texto | lhama 2 | Não | ml.inf2.8xlarge, ml.inf2.xlarge | | Meta | Code Llama 7B Python da Meta | meta-textgeneration-llama-codellama-7b-python | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.p4d.24xlarge | | Meta | Code Llama 7B Python Neuron da Meta | meta-textgenerationneuron-llama-codellama-7b-python | Geração de texto | lhama 2 | Não | ml.inf2.8xlarge, ml.inf2.xlarge | | Meta | Meta Llama 2 13B | meta-textgeneration-llama-2-13b | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 2 13B Chat da Meta | meta-textgeneration-llama-2-13b-f | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 2 13B Chat Neuron da Meta | meta-textgenerationneuron-llama-2-13b-f | Geração de texto | lhama 2 | Não | ml.inf2,24 x grande, ml.inf2,48 x grande, ml.inf2,8 x grande | | Meta | Llama 2 13B Neuron da Meta | meta-textgenerationneuron-llama-2-13b | Geração de texto | lhama 2 | Sim | ml.inf2,24 x grande, ml.inf2,48 x grande, ml.inf2,8 x grande | | Meta | Meta Llama 2 70B | meta-textgeneration-llama-2-70b | Geração de texto | lhama 2 | Sim | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Llama 2 70B Chat da Meta | meta-textgeneration-llama-2-70b-f | Geração de texto | lhama 2 | Sim | ml.g5.48xlarge, ml.p4d.24xlarge | | Meta | Llama 2 70B Chat Neuron da Meta | meta-textgenerationneuron-llama-2-70b-f | Geração de texto | lhama 2 | Não | ml.inf2.48xlarge | | Meta | Llama 2 70B Neuron da Meta | meta-textgenerationneuron-llama-2-70b | Geração de texto | lhama 2 | Não | ml.inf2.48xlarge | | Meta | Llama 2 7B Chat da Meta | meta-textgeneration-llama-2-7b-f | Geração de texto | lhama 2 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.p4d.24xlarge | | Meta | Llama 2 7B Chat Neuron da Meta | meta-textgenerationneuron-llama-2-7b-f | Geração de texto | lhama 2 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge | | Meta | Llama 2 7B Neuron da Meta | meta-textgenerationneuron-llama-2-7b | Geração de texto | lhama 2 | Sim | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge | | Meta | Llama 3 1 8B Neuron da Meta | meta-textgenerationneuron-llama-3-1-8b | Geração de texto | lhama 3.1 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Llama 3 70B da Meta | meta-textgeneration-llama-3-70b | Geração de texto | lhama 3 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 3 70B Instruct da Meta | meta-textgeneration-llama-3-70b-instruct | Geração de texto | lhama 3 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 3 70B Instruct Neuron da Meta | meta-textgenerationneuron-llama-3-70b-instruct | Geração de texto | lhama 3 | Não | ml.trn1.32xlarge | | Meta | Llama 3 70B Neuron da Meta | meta-textgenerationneuron-llama-3-70b | Geração de texto | lhama 3 | Não | ml.trn1.32xlarge | | Meta | Llama 3 8B Instruct da Meta | meta-textgeneration-llama-3-8b-instruct | Geração de texto | lhama 3 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.g6.2xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 3 8B Instruct Neuron da Meta | meta-textgenerationneuron-llama-3-8b-instruct | Geração de texto | lhama 3 | Não | ml.inf2,24 x grande, ml.inf2,48 x grande, ml.inf2,8 x grande | | Meta | Llama 3 8B Neuron da Meta | meta-textgenerationneuron-llama-3-8b | Geração de texto | lhama 3 | Não | ml.inf2,24 x grande, ml.inf2,48 x grande, ml.inf2,8 x grande | | Meta | Llama 3.1 405B FP8 da Meta | meta-textgeneration-llama-3-1-405b-fp8 | Geração de texto | lhama 3.1 | Sim | ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Llama 3.1 405B Instruct FP8 da Meta | meta-textgeneration-llama-3-1-405b-instruct-fp8 | Geração de texto | lhama 3.1 | Sim | ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Llama 3.1 70B da Meta | meta-textgeneration-llama-3-1-70b | Geração de texto | lhama 3.1 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 3.1 70B Instruct Neuron da Meta | meta-textgenerationneuron-llama-3-1-70b-instruct | Geração de texto | lhama 3.1 | Não | ml.inf2.48xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Llama 3.1 70B Neuron da Meta | meta-textgenerationneuron-llama-3-1-70b | Geração de texto | lhama 3.1 | Não | ml.inf2.48xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Llama 3.1 8B da Meta | meta-textgeneration-llama-3-1-8b | Geração de texto | lhama 3.1 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Llama 3.1 8B Instruct Neuron da Meta | meta-textgenerationneuron-llama-3-1-8b-instruct | Geração de texto | lhama 3.1 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Visão do Meta Llama 3.2 11B | meta-vlm-llama-3-2-11b-vision | Image-Text-to-Text | lhama 3.2 | Sim | ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Meta Llama 3.2 11B Vision Instruct | meta-vlm-llama-3-2-11b-vision-instruct | Image-Text-to-Text | lhama 3.2 | Sim | ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Meta Llama 3.2 1B instrui o neurônio | meta-textgenerationneuron-llama-3-2-1b-instruct | Geração de texto | lhama 3.2 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Metal Llama 3.2 1B Neurônio | meta-textgenerationneuron-llama-3-2-1b | Geração de texto | lhama 3.2 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Meta Llama 3.2 3B instrui o neurônio | meta-textgenerationneuron-llama-3-2-3b-instruct | Geração de texto | lhama 3.2 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Neurônio Meta Llama 3.2 3B | meta-textgenerationneuron-llama-3-2-3b | Geração de texto | lhama 3.2 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Visão de Meta Llama 3.2 90B | meta-vlm-llama-3-2-90b-vision | Image-Text-to-Text | lhama 3.2 | Sim | ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Meta Llama 3.2 90B Vision Instruct | meta-vlm-llama-3-2-90b-vision-instruct | Image-Text-to-Text | lhama 3.2 | Sim | ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Instrução Meta Llama 3.3 70B | meta-textgeneration-llama-3-3-70b-instruct | Geração de texto | lhama 3.3 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Meta | Meta Llama 4 Maverick 17B 128W FP8 | meta-vlm-llama-4-maverick-17b-128e-instruct-fp8 | Image-Text-to-Text | lhama 4 | Não | ml.p5en.48xlarge | | Meta | Meta Llama 4 Maverick 17B 128E instrutor | meta-vlm-llama-4-maverick-17b-128e-instruct | Image-Text-to-Text | lhama 4 | Não | ml.p5en.48xlarge | | Meta | Instrução Meta Llama 4 Scout 17B 16E | meta-vlm-llama-4-scout-17b-16e-instruct | Image-Text-to-Text | lhama 4 | Sim | ml.g6e.48xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Meta | Meta Llama Guard 3 11B Vision | meta-vlm-llama-guard-3-11b-vision | Image-Text-to-Text | lhama 3.2 | Não | ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Meta | Neurônio Meta Llama Guard 3 1B | meta-textgenerationneuron-llama-guard-3-1b | Geração de texto | lhama 3.2 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Neurônio Meta Llama Guard 3 8B | meta-textgenerationneuron-llama-guard-3-8b | Geração de texto | lhama 3.1 | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge | | Meta | Protetor Metal Llama 7B | meta-textgeneration-llama-guard-7b | Geração de texto | lhama 2 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge | | Meta | Protetor de proteção Meta Llama 86M | meta-tc-llama-prompt-guard-86m | Classificação de texto | lhama 3.1 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge | | Meta | Meta SAM 2.1 Hiera Base Plus | meta-vs-sam-2-1-hiera-base-plus | Segmentação de imagens | apache-2.0 | Não | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Meta | Metal SAM 2.1 Hiera Grande | meta-vs-sam-2-1-hiera-large | Segmentação de imagens | apache-2.0 | Não | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Meta | Metal SAM 2.1 Hiera Small | meta-vs-sam-2-1-hiera-small | Segmentação de imagens | apache-2.0 | Não | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Meta | Metal SAM 2.1 Hiera Tiny | meta-vs-sam-2-1-hiera-tiny | Segmentação de imagens | apache-2.0 | Não | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Meta | Meta-Llama-3-8B | meta-textgeneration-llama-3-8b | Geração de texto | lhama 3 | Sim | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g6.12xlarge, ml.g6e.xlarge, ml.p3.8xlarge, ml.p4d.24xlarge | | Microsoft | Phi-2 | huggingface-llm-phi-2 | Geração de texto | mit | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Microsoft | Phi-3-Mini-128K-Instruct | huggingface-llm-phi-3-mini-128k-instruct | Geração de texto | mit | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Microsoft | Phi-3-mini-4k-instruct | huggingface-llm-phi-3-mini-4k-instruct | Geração de texto | mit | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g6.12xlarge, ml.g6e.xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Microsoft | Phi-3.5-mini-instruct | huggingface-llm-phi-3-5-mini-instruct | Geração de texto | mit | Não | ml.g5.48xlarge, ml.p4d.24xlarge | | Microsoft | Detecção de transformadores de mesa | huggingface-od-microsoft-table-transformer-detection | Detecção de objetos | mit | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.xlarge | | Minimaxai | MiniMax-M2 | huggingface-llm-minimax-m2 | Geração de texto | outro | Não | ml.p4de.24xlarge | | Minimaxai | MiniMax-M2.1 | huggingface-llm-minimax-m2-1 | Geração de texto | outro | Não | ml.p4de.24xlarge, ml.p5.48xlarge | | Minimaxai | MiniMax-M2.5 | huggingface-llm-minimax-m2-5 | Geração de texto | outro | Não | ml.p5.48xlarge | | Minimaxai | MiniMax-M2.7 | huggingface-llm-minimax-m2-7 | Geração de texto | outro | Não | ml.p5en.48xlarge | | Mistralai | Mistral 7B Instruct Neuron | huggingface-llmneuron-mistral-7b-instruct | Geração de texto | apache-2.0 | Não | ml.inf2.8xlarge, ml.inf2.xlarge | | Mistralai | Mistral 7B Neuron | huggingface-llmneuron-mistral-7b | Geração de texto | apache-2.0 | Não | ml.inf2.8xlarge, ml.inf2.xlarge | | Mistralai | Mistral Nemo Base 2407 | huggingface-llm-mistral-nemo-base-2407 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge | | Mistralai | Mistral Nemo Instruct 2407 | huggingface-llm-mistral-nemo-instruct-2407 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge | | Mistralai | Mistral Pixtral-12B-2409 | huggingface-vlm-mistral-pixtral-12b-2409 | Image-Text-to-Text | apache-2.0 | Não | ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Mistralai | Mistral-7B-Instruct-v0.2 | huggingface-llm-mistral-7b-instruct | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g6.24xlarge, ml.g6e.2xlarge, ml.p3.16xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Mistralai | Mistral-7B-Instruct-v0.3 | huggingface-llm-mistral-7b-v3 | Geração de texto | apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g6.12xlarge, ml.g6e.2xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Mistralai | Mistral-7B-Instruct-v0.3 | huggingface-llm-mistral-7b-instruct-v3 | Geração de texto | apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g6.12xlarge, ml.g6e.2xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Mistralai | Mistral-7B-v0.1 | huggingface-llm-mistral-7b | Geração de texto | apache-2.0 | Sim | ml.g5.12xlarge, ml.g6.12xlarge, ml.g6e.12xlarge, ml.p3.16xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Mistralai | Mistral-Small-24B-Instruct-2501 | huggingface-llm-mistral-small-24B-Instruct-2501 | Geração de texto | apache-2.0 | Não | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Mistralai | Mistral-Small-3.1-24B-Base-2503 | huggingface-vlm-mistral-small-3-1-24b-base-2503 | Image-Text-to-Text | apache-2.0 | Não | ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge | | Mistralai | Mistral-Small-3.2-24B-Instruct-2506 | huggingface-vlm-mistral-small-3-2-24b-instruct-2506 | Image-Text-to-Text | apache-2.0 | Não | ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge | | Mistralai | Mixtral 8x7B | huggingface-llm-mixtral-8x7b | Geração de texto | apache-2.0 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Mistralai | Mixtral-8x22B V1 | huggingface-llm-mixtral-8x22B | Geração de texto | apache-2.0 | Não | ml.p4d.24xlarge, ml.p4de.24xlarge | | Mistralai | Mixtral-8x22B-Instruct-v0.1 | huggingface-llm-mistralai-mixtral-8x22B-instruct-v0-1 | Geração de texto | apache-2.0 | Não | ml.p4de.24xlarge, ml.p5.48xlarge | | Mistralai | Mixtral-8x7B-Instruct-v0.1 | huggingface-llm-mixtral-8x7b-instruct | Geração de texto | apache-2.0 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.p4d.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Moonshotai | Kimi-K2.5 | huggingface-llm-kimi-k2-5 | Geração de texto | outro | Não | ml.p5en.48xlarge | | Moritzlaurer | MoritzLaurer MDeBERTa V3 Base Xnli Multilíngue Nli 2mil7 | huggingface-zstc-moritzlaurer-mdeberta3base-xnli-mling-nli-2m7 | Zero-Shot Classificação | mit | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mosaico ml | MPT 7B BF16 | huggingface-textgeneration1-mpt-7b-bf16 | Geração de texto | Apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Mosaico ml | MPT 7B Instruct BF16 | huggingface-textgeneration1-mpt-7b-instruct-bf16 | Geração de texto | CC-BY-SA-3.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Mrm8488 | Bert Small2Bert | huggingface-summarization-bert-small2bert-cnn-dailymail-summ | Resumo de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | Incorporação de texto financeiro | mxnet-tcembedding-robertafin-base-uncased | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RoBERTa-SEC-Large | mxnet-tcembedding-robertafin-large-uncased | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RoBERTa-SEC-WIKI-Base | mxnet-tcembedding-robertafin-base-wiki-uncased | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RoBERTa-SEC-WIKI-Large | mxnet-tcembedding-robertafin-large-wiki-uncased | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Naclbit | Difusão estável Naclbit Trinart V2 | huggingface-txt2img-naclbit-trinart-stable-diffusion-v2 | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Narsil | Narsil Deberta Large Manli Zero Cls | huggingface-zstc-narsil-deberta-large-mnli-zero-cls | Zero-Shot Classificação | mit | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Nexaai | NexaAI Octopus-v2 | huggingface-llm-nexaaidev-octopus-v2 | Geração de texto | cc-by-nc-4.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Fluxo do Nexus | Fluxo do Nexus Starling-LM-7B-beta | huggingface-llm-nexusflow-starling-lm-7b-beta | Geração de texto | apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Nossa pesquisa | Hermes 2 8B Pro-Llama-3 | huggingface-llm-nousresearch-hermes-2-pro-llama-3-8B | Geração de texto | lhama 3 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Nossa pesquisa | Nous Hermes 2 SOLAR 10.7B | huggingface-llm-nousresearch-nous-hermes-2-solar-10-7b | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | Nova | Nova 2.0 Lite | nova-textgeneration-lite-v2 | Geração de texto | AWS Termos de serviço | Sim | | | Nova | Nova Lite | nova-textgeneration-lite | Geração de texto | AWS Termos de serviço | Sim | | | Nova | Nova Micro | nova-textgeneration-micro | Geração de texto | AWS Termos de serviço | Sim | | | Nova | Nova Pro | nova-textgeneration-pro | Geração de texto | AWS Termos de serviço | Sim | | | Nvidia | Nvidia 8B Llama3-ChatQA-1.5 | huggingface-llm-nvidia-llama3-chatqa-1-5-8B | Geração de texto | lhama 3 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Nvidia | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | huggingface-reasoning-nvidia-nemotron-3-nano-30b-a3b-bf16 | Reasoning | outro | Não | ml.g6e.24xlarge, ml.g7e.12xlarge | | Nvidia | NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | huggingface-reasoning-nvidia-nemotron-3-super-120b-a12b-fp8 | Reasoning | outro | Não | ml.g7e.24xlarge | | Nvidia | nvidia-nemotron3-nano-omni-30ba3b-reasoning-fp8 | huggingface-vlm-nvidia-nemotron3-nano-omni-30ba3b-reasoning-fp8 | Image-Text-to-Text | outro | Não | ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge | | Openai | gpt-oss-120b | openai-reasoning-gpt-oss-120b | Reasoning | apache-2.0 | Sim | ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Openai | gpt-oss-20b | openai-reasoning-gpt-oss-20b | Reasoning | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Openai | Base Whisper | huggingface-asr-whisper-base | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Large | huggingface-asr-whisper-large | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Large V2 | huggingface-asr-whisper-large-v2 | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Large V3 | huggingface-asr-whisper-large-v3 | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Large V3 Turbo | huggingface-asr-whisper-large-v3-turbo | Reconhecimento automático de fala | mit | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Medium | huggingface-asr-whisper-medium | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Small | huggingface-asr-whisper-small | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai | Whisper Tiny | huggingface-asr-whisper-tiny | Reconhecimento automático de fala | apache-2.0 | Não | ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Openai-Community | GPT 2 | huggingface-textgeneration-gpt2 | Geração de texto | mit | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Openai-Community | GPT-2 XL | huggingface-textgeneration1-gpt-2-xl | Geração de texto | mit | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Openai-Community | Detector OpenAI RoBerta Base | huggingface-tc-roberta-base-openai-detector | Classificação de texto | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Openai-Community | Detector OpenAI RoBerta Base | huggingface-spc-roberta-base-openai-detector | Fill-Mask | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Openai-Community | Detector OpenAI RoBerta Base | huggingface-eqa-roberta-base-openai-detector | Perguntas e respostas | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Openai-Community | Detector Roberta Large OpenAI | huggingface-tc-roberta-large-openai-detector | Classificação de texto | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Openai-Community | Detector Roberta Large OpenAI | huggingface-spc-roberta-large-openai-detector | Fill-Mask | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Openlm-Research | Open Llama 7B V2 | huggingface-llm-openlm-research-open-llama-7b-v2 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge | | Philschmid | Bart Large CNN samsum | huggingface-summarization-bart-large-cnn-samsum | Resumo de texto | mit | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Philschmid | Flan-T5 Modelo básico Fine-tuned no conjunto de dados Samsum | huggingface-text2text-flan-t5-base-samsum | Text2Geração de texto | apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Maçarico | Alexa TM 20B | pytorch-textgeneration1-alexa20b | Geração de texto | licença de software da Amazon | Não | ml.g4dn.12xlarge, ml.g5.16xlarge, ml.p3.16xlarge, ml.p3.8xlarge | | Qwen | Pré-visualização do QVQ 72B | huggingface-vlm-qvq-72b-preview | Image-Text-to-Text | outro | Não | ml.g5,48xlarge, ml.g6,48xlarge, ml.p4d.24xlarge | | Qwen | Qwen2 0,5B | huggingface-llm-qwen2-0-5b | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge | | Qwen | Instrução Qwen2 0.5B | huggingface-llm-qwen2-0-5b-instruct | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge | | Qwen | Qwen2-1.5B | huggingface-llm-qwen2-1-5b | Geração de texto | apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g6.12xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.xlarge | | Qwen | Qwen2-1.5B-Instruct | huggingface-llm-qwen2-1-5b-instruct | Geração de texto | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.2xlarge, ml.g5.xlarge, ml.g6.2xlarge, ml.g6e.xlarge, ml.p3.2xlarge | | Qwen | Qwen2-7B | huggingface-llm-qwen2-7b | Geração de texto | apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge | | Qwen | Qwen2-7B-Instruct | huggingface-llm-qwen2-7b-instruct | Geração de texto | apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge | | Qwen | Qwen2-VL-7B-Instruct | huggingface-vlm-qwen2-vl-7b-instruct | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g6.12xlarge, ml.g6e.12xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge | | Qwen | Qwen2.5 Instrução 14B | huggingface-llm-qwen2-5-14b-instruct | Geração de texto | apache-2.0 | Sim | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge | | Qwen | Qwen2.5 Instrução 32B | huggingface-llm-qwen2-5-32b-instruct | Geração de texto | apache-2.0 | Sim | ml.g5,48xlarge, ml.g6,48xlarge, ml.p4d.24xlarge | | Qwen | Qwen2.5 Codificador 32B Instruct | huggingface-llm-qwen2-5-coder-32b-instruct | Geração de texto | apache-2.0 | Não | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge | | Qwen | Qwen2.5 Codificador 7B Instruct | huggingface-llm-qwen2-5-coder-7b-instruct | Geração de texto | apache-2.0 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.16xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.p4d.24xlarge | | Qwen | Qwen2.5-72B-Instruct | huggingface-llm-qwen2-5-72b-instruct | Geração de texto | outro | Sim | ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Qwen | Qwen2.5-7B-Instruct | huggingface-llm-qwen2-5-7b-instruct | Geração de texto | apache-2.0 | Sim | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g6.12xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.xlarge | | Qwen | Qwen3 14B | huggingface-reasoning-qwen3-14b | Reasoning | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge | | Qwen | Qwen3-0.6B | huggingface-reasoning-qwen3-06b | Reasoning | apache-2.0 | Sim | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g6.12xlarge, ml.g6e.2xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Qwen | Qwen3-1.7B | huggingface-reasoning-qwen3-1-7b | Reasoning | apache-2.0 | Sim | ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge ml.g6.48xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge, ml.p3.2xlarge, ml.p4d.24xlarge | | Qwen | Qwen3-30B-A3B | huggingface-reasoning-qwen3-30b-a3b | Reasoning | apache-2.0 | Não | ml.g5.24xlarge | | Qwen | Qwen3-30B-A3B-Instruct-2507 | huggingface-reasoning-qwen3-30b-a3b-instruct-2507 | Geração de texto | apache-2.0 | Não | ml.g5,48xlarge, ml.g6,48xlarge, ml.g6e.12xlarge, ml.p4de.24xlarge | | Qwen | Qwen3-30B-A3B-Thinking-2507 | huggingface-reasoning-qwen3-30b-a3b-thinking-2507 | Reasoning | apache-2.0 | Não | ml.g6e.12xlarge | | Qwen | Qwen3-32B | huggingface-reasoning-qwen3-32b | Reasoning | apache-2.0 | Sim | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.p4d.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Qwen | Qwen3-4B | huggingface-reasoning-qwen3-4b | Reasoning | apache-2.0 | Sim | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.24xlarge, ml.g6.24xlarge ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge, ml.g6e.xlarge, ml.p4d.24xlarge | | Qwen | Qwen3-4B-Instruct-2507 | huggingface-reasoning-qwen3-4b-instruct-2507 | Reasoning | apache-2.0 | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.p4d.24xlarge | | Qwen | Qwen3-8B | huggingface-reasoning-qwen3-8b | Reasoning | apache-2.0 | Sim | ml.g4dn.12xlarge, ml.g5,12xlarge, ml.g6.12xlarge, ml.g6e.12xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Qwen | Qwen3-Coder-30B-A3B-Instruct | huggingface-reasoning-qwen3-coder-30b-a3b-instruct | Reasoning | apache-2.0 | Não | ml.g6e.24xlarge | | Qwen | Qwen3-Coder-Next | huggingface-reasoning-qwen3-coder-next | Reasoning | apache-2.0 | Não | ml.g7e.24xlarge, ml.g7e.48xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Qwen | Qwen3-Next-80B-A3B-Instruct | huggingface-reasoning-qwen3-next-80b-a3b-instruct | Geração de texto | apache-2.0 | Não | ml.g6e.48xlarge, ml.p4de.24xlarge | | Qwen | Qwen3-VL-8B-Instruct | huggingface-vlm-qwen3-vl-8b-instruct | Geração de texto | apache-2.0 | Não | ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge | | Qwen | Qwen3.5-0.8B | huggingface-vlm-qwen3-5-0-8b | Geração de texto | apache-2.0 | Não | ml.g6.4xlarge, ml.g6e.12xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.xlarge, ml.g7e.4xlarge | | Qwen | Qwen3.5-27b | huggingface-vlm-qwen3-5-27b | Geração de texto | apache-2.0 | Sim | ml.g6.48xlarge | | Qwen | Qwen3.5-27B-FP8 | huggingface-vlm-qwen3-5-27b-fp8 | Image-Text-to-Text | apache-2.0 | Não | ml.g6.24xlarge | | Qwen | Qwen3.5-2B | huggingface-vlm-qwen3-5-2b | Geração de texto | apache-2.0 | Não | ml.g6.12xlarge, ml.g6e.12xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge | | Qwen | Qwen3.5-4B | huggingface-vlm-qwen3-5-4b | Geração de texto | apache-2.0 | Sim | ml.g6.12xlarge, ml.g6e.24xlarge, ml.g7e.12xlarge, ml.g7e.2xlarge, ml.g7e.4xlarge, ml.g7e.8xlarge | | Qwen | Qwen3.5-9b | huggingface-vlm-qwen3-5-9b | Geração de texto | apache-2.0 | Sim | ml.g6.24xlarge, ml.g6.48xlarge | | Qwen | Qwen3.6-27B | huggingface-vlm-qwen3-6-27b | Image-Text-to-Text | apache-2.0 | Não | ml.g7e.12xlarge, ml.g7e.24xlarge, ml.g7e.48xlarge, ml.p5en.48xlarge | | Qwen | Qwen3.6-35B-A3B | huggingface-vlm-qwen3-6-35b-a3b | Geração de texto | apache-2.0 | Não | ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Qwen | QwQ 32B | huggingface-llm-qwq-32b | Geração de texto | apache-2.0 | Não | ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge | | Reconhecer | Reconheça Bert Based Spanish Wwm Cases Xnli | huggingface-zstc-recognai-bert-base-spanish-wwm-cased-xnli | Zero-Shot Classificação | mit | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Reconhecer | Reconheça a mídia Zeroshot Selectra | huggingface-zstc-recognai-zeroshot-selectra-medium | Zero-Shot Classificação | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Rinna | Rinna Japanese GPT NeoX 3.6B Instruction PPO | huggingface-llm-rinna-3-6b-instruction-ppo-bf16 | Geração de texto | mit | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge | | Salesforce | Salesforce \_R SFR-Embedding-2 | huggingface-textembedding-sfr-embedding-2-r | Incorporação de texto | CC-BY-NC-4.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge | | Salesforce | Salesforce SFR-Embedding-Mistral | huggingface-textembedding-sfr-embedding-mistral | Incorporação de texto | CC-BY-NC-4.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge | | Sentence-Transformers | Todos os miniLM L6 v2 | huggingface-textembedding-all-MiniLM-L6-v2 | Incorporação de texto | Apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge | | Sentence-Transformers | Todos os miniLM L6 v2 | huggingface-sentencesimilarity-all-MiniLM-L6-v2 | Similaridade de frases | apache-2.0 | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Sentence-Transformers | Paráfrase: MiniLM L12 v2 multilíngue | huggingface-textembedding-paraphrase-multilingual-MiniLM-L12-v2 | Incorporação de texto | Apache-2.0 | Não | ml.g5.xlarge, ml.g6.xlarge, ml.g6e.xlarge | | Shenzhi-Wang | Chat chinês Llama3 8B | huggingface-llm-shenzhi-wang-llama3-8B-chinese-chat | Geração de texto | lhama 3 | Não | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Snowflake | Snowflake Arctic Instruct Vllm | huggingface-llm-snowflake-arctic-instruct-vllm | Geração de texto | apache-2.0 | Não | ml.p5.48xlarge | | Speakleash | Bielik-11B-v3.0-Instruct | huggingface-llm-bielik-11b-v3-0-instruct | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g6.12xlarge, ml.g6e.12xlarge, ml.g7e.2xlarge, ml.p4d.24xlarge, ml.p5en.48xlarge | | Schleifer | Distilbart CNN 12-6 | huggingface-summarization-distilbart-cnn-12-6 | Resumo de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Schleifer | Distilbart CNN 6-6 | huggingface-summarization-distilbart-cnn-6-6 | Resumo de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Schleifer | Resumo de texto | huggingface-summarization-distilbart-xsum-1-1 | Resumo de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Estabilidade ai | Japanese StableLM Instruct Alpha 7B v2 | model-textgenerationjp-japanese-stablelm-instruct-alpha-7b-v2 | Geração de texto | Apache-2.0 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Estabilidade ai | Difusão estável 2 | model-txt2img-stabilityai-stable-diffusion-v2 | Text-to-Image | creativml-openrail\+\+-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Estabilidade ai | Difusão estável de 2 profundidades FP16 | model-depth2img-stable-diffusion-2-depth-fp16 | Image-to-Image | creativml-openrail\+\+-m | Não | ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Estabilidade ai | Difusão estável 2 FP16 | model-txt2img-stabilityai-stable-diffusion-v2-fp16 | Text-to-Image | creativml-openrail\+\+-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Estabilidade ai | Difusão estável 2: pintura embutida | model-inpainting-stabilityai-stable-diffusion-2-inpainting | Image-to-Image | creativml-openrail\+\+-m | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Estabilidade ai | Difusão estável 2: pintura embutida FP16 | model-inpainting-stabilityai-stable-diffusion2-inpainting-fp16 | Image-to-Image | creativml-openrail\+\+-m | Não | ml.g4dn.xlarge, ml.g5.2xlarge, ml.p3.2xlarge | | Estabilidade ai | Difusão estável 2: pintura embutida FP16 | model-inpainting-stabilityai-stable-diffusion-2-inpainting-fp16 | Image-to-Image | creativml-openrail\+\+-m | Não | ml.g4dn.xlarge, ml.g5.2xlarge, ml.p3.2xlarge | | Estabilidade ai | Stable Diffusion 2.1 | model-txt2img-stabilityai-stable-diffusion-v2-1-base | Text-to-Image | creativml-openrail\+\+-m | Sim | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Estabilidade ai | Difusão estável 2.1 Neurônio | huggingface-txt2imgneuron-stabilityai-stable-diffusion-v2-1 | Text-to-Image | creativml-openrail\+\+-m | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge | | Estabilidade ai | Upscaler de difusão estável x4 FP16 | model-upscaling-stabilityai-stable-diffusion-x4-upscaler-fp16 | Image-to-Image | openrail\+\+ | Não | ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Estabilidade ai | Stable Diffusion XL 1.0 (código aberto) | model-imagegeneration-stabilityai-stable-diffusion-xl-base-1-0 | Text-to-Image | openrail\+\+ | Não | ml.g5.16xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Estabilidade ai | Neurônio XL de base 1.0 de difusão estável | huggingface-txt2imgneuron-stabilityai-stable-diffusion-xlbase1 | Text-to-Image | openrail\+\+ | Não | ml.inf2.24xlarge, ml.inf2.48xlarge, ml.inf2.8xlarge, ml.inf2.xlarge | | Swiss-Ai | Apertus 70B 2509 | huggingface-llm-apertus-70b-2509 | Geração de texto | apache-2.0 | Não | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Swiss-Ai | Apertus 70B Instruct 2509 | huggingface-llm-apertus-70b-instruct-2509 | Geração de texto | apache-2.0 | Não | ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Swiss-Ai | Apertus 8B Instruct 2509 | huggingface-llm-apertus-8b-instruct-2509 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.48xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge .g6e.xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | O cara | Mistral 7B AAA OpenOrca | huggingface-llm-thebloke-mistral-7b-openorca-awq | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge | | O cara | Mistral 7V GPTQ OpenOrca | huggingface-llm-mistral-7b-openorca-gptq | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | O cara | Mixtral 8x7B Instruct GPTQ | huggingface-llm-mixtral-8x7b-instruct-gptq | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | O nnper | GTE Grande | huggingface-sentencesimilarity-gte-large | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | O nnper | GTE pequeno | huggingface-sentencesimilarity-gte-small | Similaridade de frases | mit | Sim | ml.c6i.xlarge, ml.g4dn.2xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.p3.2xlarge | | Tiuae | Falcon 180B BF16 | huggingface-llm-falcon-180b-bf16 | Geração de texto | desconhecido | Não | ml.p4de.24xlarge, ml.p5.48xlarge | | Tiuae | Falcon 180B Chat BF16 | huggingface-llm-falcon-180b-chat-bf16 | Geração de texto | desconhecido | Não | ml.p4de.24xlarge, ml.p5.48xlarge | | Tiuae | Falcon 40B BF16 | huggingface-llm-falcon-40b-bf16 | Geração de texto | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Tiuae | Falcon 40B Instruct BF16 | huggingface-llm-falcon-40b-instruct-bf16 | Geração de texto | apache-2.0 | Sim | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Tiuae | Falcon 7B BF16 | huggingface-llm-falcon-7b-bf16 | Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Tiuae | Falcon 7B Instruct BF16 | huggingface-llm-falcon-7b-instruct-bf16 | Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Tiuae | Falcon RW 1B | huggingface-llm-tiiuae-falcon-rw-1b | Geração de texto | apache-2.0 | Não | ml.g5.2xlarge | | Tiuae | Falcon-H1-0.5B-Instruct | huggingface-llm-falcon-h1-0-5b-instruct | Geração de texto | outro | Não | ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.2xlarge, ml.g5.2xlarge 48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge, ml.p3.2xlarge, ml.p4d.24xlarge | | Tiuae | Falcon-H1-1.5B-Deep-Instruct | huggingface-llm-falcon-h1-1-5b-deep-instruct | Geração de texto | outro | Não | ml.g5.16xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g6.16xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.16xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.4xlarge 8xlarge, ml.g6e.xlarge | | Tiuae | Falcon-H1-1.5B-Instruct | huggingface-llm-falcon-h1-1-5b-instruct | Geração de texto | outro | Não | ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.24xlarge 2xlarge, ml.g6e.48xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge | | Tiuae | Falcon-H1-34B-Instruct | huggingface-llm-falcon-h1-34b-instruct | Geração de texto | outro | Não | ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge | | Tiuae | Falcon-H1-3B-Instruct | huggingface-llm-falcon-h1-3b-instruct | Geração de texto | outro | Não | ml.g6e.16xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge | | Tiuae | Falcon-H1-7B-Instruct | huggingface-llm-falcon-h1-7b-instruct | Geração de texto | outro | Não | ml.g6e.12xlarge, ml.g6e.24xlarge | | Tiuae | Falcon2-11B | huggingface-llm-falcon2-11b | Geração de texto | desconhecido | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Tiuae | Falcon3-10B-Base | huggingface-llm-falcon-3-10B-base | Geração de texto | outro | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Tiuae | Falcon3-10B-Instruct | huggingface-llm-falcon-3-10B-Instruct | Geração de texto | outro | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.xlarge | | Tiuae | Falcon3-1B-Instruct | huggingface-llm-falcon-3-1B-Instruct | Geração de texto | outro | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.g6.xlarge, ml.g6e.xlarge, ml.p3.2xlarge, ml.p4d.24xlarge | | Tiuae | Falcon3-3B-Base | huggingface-llm-falcon-3-3B-base | Geração de texto | outro | Não | ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.2xlarge, ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Tiuae | Falcon3-3B-Instruct | huggingface-llm-falcon-3-3B-Instruct | Geração de texto | outro | Não | ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g4dn.4xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.xlarge, ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.16xlarge g6.24xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.8xlarge, ml.g6e.xlarge, ml.p3.2xlarge | | Tiuae | Falcon3-7B-Base | huggingface-llm-falcon-3-7B-base | Geração de texto | outro | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | Tiuae | Falcon3-7B-Instruct | huggingface-llm-falcon-3-7B-Instruct | Geração de texto | outro | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.large | | Tinyllama | Tiny Llama 1.1B | huggingface-llm-tinyllama-1-1b-intermediate-step-1431k-3 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge | | Tinyllama | Tiny Llama 1.1B Chat V0.6 | huggingface-llm-tinyllama-tinyllama-1-1b-chat-v0-6 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge | | Tinyllama | Tiny Llama 1.1B Chat V1 | huggingface-llm-tinyllama-tinyllama-1-1b-chat-v1-0 | Geração de texto | apache-2.0 | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.2xlarge | | Computador Together | RedPajama INCITE Chat 3B V1 | huggingface-textgeneration1-redpajama-incite-chat-3B-v1-fp16 | Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Computador Together | RedPajama INCITE Chat 7B V1 | huggingface-textgeneration1-redpajama-incite-chat-7B-v1-fp16 | Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Computador Together | RedPajama INCITE Instruct 3B V1 | huggingface-textgeneration1-redpajama-incite-instruct-3Bv1fp16 | Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Computador Together | RedPajama INCITE Instruct 7B V1 | huggingface-textgeneration1-redpajama-incite-instruct-7B1fp16 | Geração de texto | apache-2.0 | Sim | ml.g5.16xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge | | Tokyotech-Llm | Swallow-7b-instruct-hf | huggingface-llm-swallow-7b-instruct-hf | Geração de texto | lhama 2 | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.2xlarge, ml.g5.48xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.xlarge, ml.g6.24xlarge, ml.g6.24xlarge ml.g6.2xlarge, ml.g6.48xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.p3.16xlarge, ml.p3.8xlarge | | Volrath50 | difusão de cartas de fantasia volrath50 | huggingface-txt2img-volrath50-fantasy-card-diffusion | Text-to-Image | creativml-openrail-m | Não | ml.g4dn.2xlarge, ml.g4dn.xlarge, ml.p3.2xlarge | | Gravador | Writer Palmyra Small | huggingface-llm-writer-palmyra-small | Geração de texto | apache-2.0 | Não | ml.g5.2xlarge | ------ #### [ Proprietary Models (121) ] Modelos de fundação proprietários são oferecidos por fornecedores terceirizados por meio da Amazon SageMaker JumpStart. Para usar um modelo básico proprietário, você deve primeiro assinar o modelo no AWS Marketplace. Depois de se inscrever, você pode localizar e implantar o modelo básico no Amazon SageMaker Studio. | Nome do modelo | ID do modelo | Tarefa | Fine-tunable | Tipos de instância de inferência compatíveis | | --- | --- | --- | --- | --- | | A.X 4.0 Luz | sk-telecom-ax4-light | Geração de texto | Não | ml.g5.2xlarge | | Respostas contextuais do AI21 | ai21-contextual-answers | Geração de texto | Não | ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.g4dn.12xlarge | | Luz AI21 Jurassic-2 | ai21-jurassic-2-light | Geração de texto | Não | ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | AI21 Jurassic-2 Mid | ai21-jurassic-2-grande-instruct | Geração de texto | Não | ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.g4dn.12xlarge | | AI21 Ultra Jurassic-2 | ai21-jurassic-2-jumbo-instruct | Geração de texto | Não | ml.g5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Paráfrase AI21 | ai21-paraphrase | Geração de texto | Não | ml.g4dn.2xlarge | | AI21 Resumir | ai21-summarization | Geração de texto | Não | ml.g4dn.4xlarge, ml.g4dn.12xlarge, ml.g5.xlarge | | Arcee Lite | arcee-lite | Geração de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g6.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.16xlarge | | Arcee SuperNova | arcee-supernova | Geração de texto | Não | ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Arcee Virtuoso Small | arcee-virtuoso-small | Geração de texto | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g5.48xlarge, ml.g6.48xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p4de.24xlarge, ml.p4de.24xlarge .p 5.48 x grande | | Bria 2.2HD Comercial Text-to-image | bria-ai-2-2-hd-commercial | ReRank | Não | ml.g5.2xlarge, ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Bria 2.3 Comercial Text-to-image | bria-ai-2-3-commercial | ReRank | Não | ml.g5.2xlarge, ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Bria 2.3 Fast Commercial Text-to-image | bria-ai-2-3-fast-commercial | ReRank | Não | ml.g5.2xlarge, ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Comando Cohere R (A100) | cohere-command-r-a100 | Geração de texto | Não | ml.p4de.24xlarge | | Comando Cohere R (H100) | cohere-command-r-h100 | Geração de texto | Não | ml.p5.48xlarge | | Comando Cohere R\+ (A100) | cohere-command-r-plus-a100 | Geração de texto | Não | ml.p4de.24xlarge | | Comando Cohere R\+ (H100) | cohere-command-r-plus-h100 | Geração de texto | Não | ml.p5.48xlarge | | Cohere Embed 4 | cohere-embed-v4-0 | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g6.xlarge, ml.g6.2xlarge | | Cohere Embed Light Model v3 - Inglês | cohere-embed-light-english | Incorporação de texto | Não | ml.p3.2xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Cohere Embed Light v3 - Multilíngue | cohere-embed-light-multilingual | Incorporação de texto | Não | ml.p3.2xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Cohere Embed Model 3 - Multilíngue | cohere-embed-multilingual | Incorporação de texto | Não | ml.p3.2xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Cohere Embed Model v3 - Inglês | cohere-embed-english | Incorporação de texto | Não | ml.p3.2xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Modelo Cohere Rerank 2 - Inglês | cohere-rerank-english-v2 | ReRank | Não | ml.p3.2xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Modelo Cohere Rerank 2 - Multilíngue | cohere-rerank-multilingual-v2 | ReRank | Não | ml.p3.2xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Modelo Cohere Rerank 3 - Inglês | cohere-rerank-v3-english | ReRank | Não | ml.g5.xlarge, ml.g5.2xlarge | | Modelo Cohere Rerank 3 - Multilíngue | cohere-rerank-v3-multilingual | ReRank | Não | ml.g5.xlarge, ml.g5.2xlarge | | Modelo Cohere Rerank 3 Nimble - Inglês | cohere-rerank-nimble-english | ReRank | Não | ml.g5.xlarge, ml.g5.2xlarge | | Modelo Cohere Rerank 3 Nimble - Multi | cohere-rerank-nimble-multi | ReRank | Não | ml.g5.xlarge, ml.g5.2xlarge | | Cohere Rerank v3.5 | cohere-rerank-v3-5 | Incorporação de texto | Não | ml.g6.xlarge, ml.g6.2xlarge, ml.g5.xlarge, ml.g5.2xlarge | | Cohere Rerank v4.0 Rápido | cohere-rerank-v4-0-fast | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.p5.4xlarge | | Cohere Rerank v4.0 Pro | cohere-rerank-v4-0-pro | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.p5.4xlarge | | Comando A (A100) | cohere-command-a-a100 | Geração de texto | Não | ml.p4de.24xlarge | | Comando A (H100) | cohere-command-a-h100 | Geração de texto | Não | ml.p5.48xlarge | | Comando R 08-2024 (H100) | cohere-command-r-08-2024-h100 | Geração de texto | Não | ml.p5.48xlarge | | Comando R\+ 08-2024 (H100) | cohere-command-r-plus-08-2024-h100 | Geração de texto | Não | ml.p5.48xlarge | | OCR de documentos | upstage-document-ocr | Reconhecimento óptico de caracteres | Não | ml.g5.2xlarge | | Análise de documentos | upstage-document-layout-analysis | Reconhecimento óptico de caracteres | Não | ml.g5.2xlarge, ml.g6.2xlarge, ml.p3.2xlarge | | Embutir | upstage-solar-embedding-large | Incorporação de texto | Não | ml.g5.2xlarge | | ESM3-open | evolutionary-scale-esm3 | Geração multimodal | Não | ml.g5.4xlarge, ml.g5.8xlarge | | Evo2-NIM | nvidia-evo2-nim | Geração de texto | Não | ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | EXAONE Atelier - Imagem em texto | lgresearch-exaone | Geração de texto Image2Text | Não | ml.g5.xlarge, ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlarge | | Gretel Navigator Tabular | gretel-navigator-tabular | Geração de texto | Não | ml.g5.xlarge, ml.g5.2xlarge | | H-Optimus-0 | bioptimus-h-optimus-0 | Extração de características | Não | ml.g5.xlarge | | IBM Granite 20B Code Instruct – 8K | ibm-granite-20b-code-instruct-8k | Geração de texto | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | IBM Granite 3.0 2B Instruct | granite-3-0-2b-instruct | Geração de texto | Não | ml.p4d.24xlarge, ml.p5.48xlarge | | IBM Granite 3.0 8B Instruct | granite-3-0-8b-instruct | Geração de texto | Não | ml.p4d.24xlarge, ml.p5.48xlarge | | IBM Granite 3.2 Instruct 2B | ibm-granite-3-2-2b-instruct | Geração de texto | Não | ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge, ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge ml.g6.48xlarge | | IBM Granite 3.2 Instruct 8B | ibm-granite-3-2-8b-instruct | Geração de texto | Não | ml.g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4d.24xlarge, ml.p4d.24xlarge, ml.p4d.24xlarge, ml.p 5.48xlarge | | IBM Granite 34B Code Instruct – 8K | ibm-granite-34b-code-instruct-8k | Geração de texto | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | IBM Granite 3B Code Instruct – 128K | ibm-granite-3b-code-instruct-128k | Geração de texto | Não | ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | IBM Granite 4.0 h-micro | ibm-granite-4-0-h-micro | Geração de texto | Não | ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | IBM Granite 4.0 h pequeno | ibm-granite-4-0-h-small | Geração de texto | Não | ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | IBM Granite 4.0 minúsculo | ibm-granite-4-0-h-tiny | Geração de texto | Não | ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge | | IBM Granite 8B Code Instruct – 128K | ibm-granite-8b-code-instruct-128k | Geração de texto | Não | ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | ixi- GEN-Fin-7.8B | lg-ixi-gen | Geração de texto | Não | ml.g5.4xlarge | | JetBrains Tudo AI Mellum | jbai-mellum-all | text2geração de texto | Não | ml.g5.2xlarge, ml.g6.2xlarge, ml.g6e.xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | JetBrains AI Mellum Kotlin | jbai-mellum-kotlin | text2geração de texto | Não | ml.g5.2xlarge, ml.g6.2xlarge, ml.g6e.xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | JetBrains IA em Python | jbai-mellum-python | text2geração de texto | Não | ml.g5.2xlarge, ml.g6.2xlarge, ml.g6e.xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge | | Jina Embeddings v2 Base - pt | jinaai-embeddings-v2-base-en | Incorporação de texto | Não | ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | KARAKURI LM 8x7b instruct | karakuri-lm-8x7b-instruct | Geração de texto | Não | ml.g5,48xlarge, ml.g6,48xlarge | | LightOn Lyra-Fr 10B | lighton-lyra-fr | Geração de texto | Não | ml.p4d.24xlarge | | LightOn Mini-instruct 40B | lighton-mini-instruct40b | Geração de texto | Não | ml.p4d.24xlarge | | Líquido LFM 40B (A100) | liquid-lfm-40b-a100 | Geração de texto | Não | ml.p4d.24xlarge | | Líquido LFM 40B (H100) | liquid-lfm-40b-h100 | Geração de texto | Não | ml.p5.48xlarge | | Líquido LFM 40B (L40S) | liquid-lfm-40b-l40s | Geração de texto | Não | ml.g6e.12xlarge | | Líquido LFM 7B (L40S) | liquid-lfm-7b-l40s | Geração de texto | Não | ml.g6e.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.16xlarge | | Lama 3.1 Nemotron Nano 8B V1 | nvidia-nemotron-nano-8b-nim | Geração de texto | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.16xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Llama 3.1 SuperNova Lite | arcee-llama-3-1-supernova-lite | Geração de texto | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.16xlarge | | Microsserviço NIM Llama 3.2 NVRERankQA1b | nvidia-llama3-2-nv-rerankqa-1b-v2-nim | Geração de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge .g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge, ml.g6e.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge 6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4de.24xlarge | | Lama 3.3 Nemotron Super 49B V1 | nvidia-nemotron-super-49b-nim | Geração de texto | Não | ml.g5.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Lama 3.3 Nemotron Super 49B V1.5 | nvidia-nemotron-super-49b-nim-1-5 | Geração de texto | Não | ml.g5.48xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Llama Spark | arcee-llama-spark | Geração de texto | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.16xlarge | | Llama-3-Varco-Offsetbias-8B | ncsoft-llama-3-varco-offsetbias-8b | Geração de texto | Não | ml.g5.12xlarge | | Llama-3.1-8B-Instruct com Stained Glass Transform Support | protopia-llama-3-1-8b-instruct | Geração de texto | Não | ml.g4dn.12xlarge, ml.g5.4xlarge, ml.g5.16xlarge | | Llama-3.2-NV-EmbedQA-1B-v2 | nvidia-llama3-2-nv-embedqa-1b-v2-nim | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge, ml.g6.8xlarge .g6.12xlarge, ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge, ml.g6e.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge, ml.g6e.12xlarge 6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4de.24xlarge | | MARS6 | cambai-mars6 | Texto para áudio | Não | ml.g4dn.2xlarge, ml.g6.2xlarge | | Medical LLM – Medium | john-snow-labs-medical-summarization-qa-8b | Resumo de texto | Não | ml.g5.2xlarge, ml.g4dn.12xlarge | | Medical LLM – Small | john-snow-labs-summarization-qa | Resumo de texto | Não | ml.g5.12xlarge | | Tradução de texto médico (EN-ES) | john-snow-labs-medical-translation-en-es | Tradução | Não | ml.g5.2xlarge | | Mercúrio | inception-mercury | Geração de texto | Não | ml.p5.48xlarge | | Codificador Mercury | inception-mercury-coder | Geração de texto | Não | ml.p5.48xlarge | | pesquisa msa | nvidia-nim-msa-search-v2-1 | Geração de texto | Não | ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p5.48xlarge, ml.p4de.24xlarge, ml.p5en.48xlarge | | Nemotron nano 9b v2 | nvidia-nemotron-nano-9b-v2 | Geração de texto | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6e.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.8xlarge e.16xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.4xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | análise de nemotrons | nvidia-nemotron-parse | Geração de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6e.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge xlarge, ml.g6e.16xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.4xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | NEXUS da Fundamental | fundamental-technologies-nexus | Classificação | Não | ml.g4dn.8xlarge, ml.p5en.48xlarge | | Texto de incorporação Nomic v1.5 | nomic-embed-text | Incorporação de texto | Não | ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g5.xlarge, ml.g5.2xlarge xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | Nomic Embed Vision v1.5 | nomic-embed-image | Incorporação de texto | Não | ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g5.xlarge, ml.g5.2xlarge xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | NVIDIA Cosmos Reason-1-7B | nvidia-nim-cosmos-reason1-7b | Geração de texto | Não | ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6e.xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.16xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.x48large, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.4xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | Microsserviço NIM NVIDIA Nemotron-4 15B | nvidia-nemotron-4-15b-nim | Geração de texto | Não | ml.g5.12xlarge, ml.g5.24xlarge | | NVIDIA ParakeetVTDT 0.6B v2 | nvidia-parakeetvtdt-0-6b-v2 | Geração de texto Audio2 | Não | ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.12xlarge, ml.g6e.16xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.12xlarge ml.g6.16xlarge, ml.g6.24xlarge, ml.g6.48xlarge | | NVIDIA-Parakeet-1-1b-CTC-EN-US-ASR | nvidia-parakeet-1-1b-ctc-en-us-asr | Geração de texto Audio2 | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.8xlarge, ml.g6.16xlarge, ml.g6.12xlarge, ml.g6.24xlarge, ml.g6.48xlarge, ml.g6e.2xlarge, ml.g6e.4xlarge, ml.g6e.8xlarge, ml.g6e.16xlarge, ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Orbe | orbital-materials-orb | Modelagem científica | Não | ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p4d.24xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge | | PLaMo Implantação privada | preferred-networks-plamo-api | Geração de texto | Não | ml.p4d.24xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | ProteinMPNN-NIM | nvidia-nim-proteinmpnn-v1-0-2 | Geração de texto | Não | ml.g6e.12xlarge, ml.g6e.24xlarge, ml.g6e.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, ml.p5en.48xlarge | | rerank-lite-1 Reranker | voyage-rerank-lite-1-reranker | ReRank | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge | | Solar Mini - Quant | upstage-solar-mini-chat-quant | Geração de texto | Não | ml.g5.2xlarge | | Solar Pro - Quant | upstage-solar-pro-quantized | Geração de texto | Não | ml.g5.12xlarge | | Solar Pro 2 | upstage-solar-pro | Geração de texto | Não | ml.p4d.24xlarge, ml.p5.48xlarge | | Sonic 3 SageMaker | cartesia-sonic-3-sagemaker | Texto para áudio | Não | ml.g6e.xlarge | | Stable Diffusion 3.5 Large | stabilityai-stable-diffusion-3-5-large | Texto para imagem | Não | ml.p5.48xlarge | | Stable Diffusion XL 1.0 | stabilityai-sdxl-1-0 | Texto para imagem | Não | ml.g5.2xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Difusão estável XL Beta 0.8 | stabilityai-sdxl-beta-0-8 | Texto para imagem | Não | ml.g5.xlarge | | Stockmark-LLM-13b | stockmark-llm-13b | Geração de texto | Não | ml.g5.2xlarge | | BARCO LLM KO-1.3B-IST | ncsoft-ko-1-3b-ist | Geração de texto | Não | ml.g5.2xlarge, ml.g5.4xlarge, ml.g4dn.2xlarge | | BARCO LLM KO-6.4B-IST | ncsoft-ko-6-4b-ist | Geração de texto | Não | ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge | | BARCO LLM KO/EN-13B-IST | ncsoft-ko-13b-ist | Geração de texto | Não | ml.g5.12xlarge, ml.g4dn.12xlarge | | Modelo de incorporação voyage-2 | voyage-2-embedding | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge | | Modelo de incorporação voyage-3 | voyage-3-embedding | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g6.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.16xlarge | | Modelo de incorporação grande voyage-3 | voyage-3-large-embedding | Incorporação de texto | Não | ml.g6.2xlarge, ml.g5.xlarge, ml.g5.8xlarge, ml.g6.4xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g6.8xlarge, ml.g6.xlarge | | Modelo de incorporação voyage-3.5 | voyage-3-5-embedding | Incorporação de texto | Não | ml.g5.16xlarge, ml.g6.16xlarge, ml.g6.2xlarge, ml.g5.xlarge, ml.g5.8xlarge, ml.g6.4xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g6.xlarge | | Modelo de incorporação voyage-3.5-lite | voyage-3-5-lite-embedding | Incorporação de texto | Não | ml.g6.16xlarge, ml.g6.2xlarge, ml.g5.xlarge, ml.g5.8xlarge, ml.g6.4xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g6.8xlarge, ml.g5.16xlarge, ml.g6.xlarge | | Modelo de incorporação voyage-code-2 | voyage-code-2-embedding | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g6.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.16xlarge | | Modelo de incorporação voyage-code-3 | voyage-code-3-embedding | Incorporação de texto | Não | ml.g6.16xlarge, ml.g6.2xlarge, ml.g5.xlarge, ml.g5.8xlarge, ml.g6.4xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g6.8xlarge, ml.g5.16xlarge, ml.g6.xlarge | | Modelo de incorporação voyage-large-2 | voyage-large-2-embedding | Incorporação de texto | Não | ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g6.xlarge, ml.g6.2xlarge, ml.g6.4xlarge, ml.g6.4xlarge, ml.g6.16xlarge | | Widn Tower Anthill | widn-tower-anthill | Tradução | Não | ml.g5.xlarge | | Widn Tower Sugarloaf | widn-tower-sugarloaf | Tradução | Não | ml.g5.12xlarge | | Torre Eólica Vesúvio | widn-llama3-tower-vesuvius | Tradução | Não | ml.g5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge | | Motor de visão AI Woven City | wovenbytoyota-woven-city-ai-vision-engine | Geração multimodal | Não | ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge | | Escritor Palmyra-Fin-70B-32K | writer-palmyra-fin-70b-32k | Geração de texto | Não | ml.p4d.24xlarge | | Escritor Palmyra-Med-70B-32K | writer-palmyra-med-70b-32k | Geração de texto | Não | ml.p4d.24xlarge | | Escritor Palmyra-X-004 | writer-palmyra-x-004 | Geração de texto | Não | ml.p5.48xlarge | ------ #### [ Built-in Algorithms (135) ] SageMaker JumpStart A Amazon fornece modelos pré-treinados e específicos para tarefas comuns de visão computacional, como classificação de imagens, detecção de objetos e segmentação de imagens. Esses modelos são criados em estruturas de aprendizado profundo estabelecidas (PyTorch,TensorFlow,MXNet) e estão prontos para serem implantados ou ajustados em seus próprios dados. | Fornecedor | Nome do modelo | ID do modelo | Tarefa | Licença | Fine-tunable | Tipos de instância de inferência compatíveis | | --- | --- | --- | --- | --- | --- | --- | | Mxnet | RCNN 101 V1d ResNet mais rápido | mxnet-od-faster-rcnn-resnet101-v1d-coco | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RCNN 101 V1d ResNet mais rápido | mxnet-od-faster-rcnn-fpn-resnet101-v1d-coco | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RCNN 50 V1b ResNet mais rápido | mxnet-od-faster-rcnn-resnet50-v1b-voc | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RCNN 50 V1b ResNet mais rápido | mxnet-od-faster-rcnn-resnet50-v1b-coco | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | RCNN 50 V1b ResNet mais rápido | mxnet-od-faster-rcnn-fpn-resnet50-v1b-coco | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | FCN ResNet 101 ADE20K | mxnet-semseg-fcn-resnet101-ade | Segmentação de imagens | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | VOC FCN ResNet 101 Pascal | mxnet-semseg-fcn-resnet101-voc | Segmentação de imagens | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | FCN ResNet 50 ADE20K | mxnet-semseg-fcn-resnet50-ade | Segmentação de imagens | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | Segmentação de instância | mxnet-is-mask-rcnn-fpn-resnet101-v1d-coco | Segmentação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | MÁSCARA RCNN FPN RESNET18 COCO | mxnet-is-mask-rcnn-fpn-resnet18-v1b-coco | Segmentação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | MÁSCARA RCNN FPN RESNET50 COCO | mxnet-is-mask-rcnn-fpn-resnet50-v1b-coco | Segmentação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | MÁSCARA RCNN RESNET18 COCO | mxnet-is-mask-rcnn-resnet18-v1b-coco | Segmentação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | Detecção de objetos | mxnet-od-ssd-512-mobilenet1-0-coco | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | Segmentação semântica | mxnet-semseg-fcn-resnet101-coco | Segmentação de imagens | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD 512 50 ResNet V1 | mxnet-od-ssd-512-resnet50-v1-coco | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD 1.0 MobileNet | mxnet-od-ssd-512-mobilenet1-0-voc | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD ResNet 5.0 V1 | mxnet-od-ssd-512-resnet50-v1-voc | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD VGG 16 Atrous 300 | mxnet-od-ssd-300-vgg16-atrous-voc | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD VGG 16 Atrous 512 | mxnet-od-ssd-512-vgg16-atrous-coco | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD VG16 Atrous 300 | mxnet-od-ssd-300-vgg16-atrous-coco | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | SSD VGG16 Atrous 512 | mxnet-od-ssd-512-vgg16-atrous-voc | Detecção de objetos | apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | YOLO V3 53 DarkNet | mxnet-od-yolo3-darknet53-voc | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | YOLO V3 53 DarkNet | mxnet-od-yolo3-darknet53-coco | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | YOLO V3 1.0 MobileNet | mxnet-od-yolo3-mobilenet1-0-voc | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Mxnet | YOLO V3 1.0 MobileNet | mxnet-od-yolo3-mobilenet1-0-coco | Detecção de objetos | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Maçarico | SqueezeNet 1 | pytorch-ic-squeezenet1-1 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | AlexNet | pytorch-ic-alexnet | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | DenseNet 121 | pytorch-ic-densenet121 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | DenseNet 169 | pytorch-ic-densenet169 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | FRCNN MobileNet V3 grande 320 FPN | pytorch-od1-fasterrcnn-mobilenet-v3-large-320-fpn | Detecção de objetos | cláusula bsd-3 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Maçarico | FPN grande FRCNN MobileNet V3 | pytorch-od1-fasterrcnn-mobilenet-v3-large-fpn | Detecção de objetos | cláusula bsd-3 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Maçarico | GoogLeNet | pytorch-ic-googlenet | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | Classificação de imagens | pytorch-ic-mobilenet-v2 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | Detecção de objetos | pytorch-od1-fasterrcnn-resnet50-fpn | Detecção de objetos | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Maçarico | ResNet 101 | pytorch-ic-resnet101 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | ResNet 152 | pytorch-ic-resnet152 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | ResNet 18 | pytorch-ic-resnet18 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | ResNet 34 | pytorch-ic-resnet34 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | ResNet 50 | pytorch-ic-resnet50 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | Resnext 50 | pytorch-ic-resnext50-32x4d | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | ShuffleNet V2 | pytorch-ic-shufflenet-v2-x1-0 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | SSD | pytorch-od-nvidia-ssd | Detecção de objetos | cláusula bsd-3 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Maçarico | OVO 1 | pytorch-ic-vgg11 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | OVO 11 BILHÕES | pytorch-ic-vgg11-bn | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | OVO 13 BILHÕES | pytorch-ic-vgg13-bn | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | OVO 16 | pytorch-ic-vgg16 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | OVO DE 16 BILHÕES | pytorch-ic-vgg16-bn | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | OVO 19 | pytorch-ic-vgg19 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | VGG-13 | pytorch-ic-vgg13 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Maçarico | Largo ResNet 101 | pytorch-ic-wide-resnet101-2 | Classificação de imagens | cláusula bsd-3 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge | | Tensorflow | Base ALBERT | tensorflow-tc-albert-en-base | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | Base BERT cased | tensorflow-tc-bert-en-cased-L-12-H-768-A-12-2 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | Base BERT MEDLINE/PubMed | tensorflow-tc-experts-bert-pubmed-1 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | Estojo multilíngue Base BERT | tensorflow-tc-bert-multi-cased-L-12-H-768-A-12-2 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT grande uncased | tensorflow-tc-bert-en-uncased-L-24-H-1024-A-16-2 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT Small, sem estojo L-10 H-128 | tensorflow-tcembedding-bert-en-uncased-L-10-H-128-A-2-2 | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | BERT Small, sem estojo L-12 H-256 | tensorflow-tcembedding-bert-en-uncased-L-12-H-256-A-4 | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | BERT Small, sem estojo L-12 H-768 | tensorflow-tcembedding-bert-en-uncased-L-12-H-768-A-12-2 | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | BERT Small, sem estojo L-4 H-768 | tensorflow-tcembedding-bert-en-uncased-L-4-H-768-A-12-2 | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | BiT-M R101x1 | tensorflow-ic-bit-m-r101x1-ilsvrc2012-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | BiT-M Vetor de características R101x1 | tensorflow-icembedding-bit-m-r101x1-ilsvrc2012-featurevector-1 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | BiT-M R50x1 ImageNet-21k | tensorflow-ic-bit-m-r50x1-imagenet21k-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | Ato S 24 224 | tensorflow-ic-cait-s24-224 | Classificação de imagens | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | CenterNet ResNet-v1-101 | tensorflow-od-centernet-resnet101v1-fpn-512x512-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | CenterNet ResNet-v1-50 | tensorflow-od-centernet-resnet50v1-fpn-512x512-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | Editar Tiny Distilled Patch 16 224 | tensorflow-ic-deit-tiny-distilled-patch16-224 | Classificação de imagens | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | EfficientNet B0 | tensorflow-ic-efficientnet-b0-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | EfficientNet B1 | tensorflow-ic-efficientnet-b1-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | EfficientNet Vetor de características B1 | tensorflow-icembedding-efficientnet-b1-featurevector-1 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | EfficientNet B3 | tensorflow-ic-efficientnet-b3-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | EfficientNet B7 | tensorflow-ic-efficientnet-b7-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.9xlarge, ml.g4dn.8xlarge, ml.p3.8xlarge | | Tensorflow | EfficientNet V2 Pequeno ImageNet-1k | tensorflow-ic-efficientnet-v2-imagenet1k-s | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | EfficientNet V2 ImageNet-21k Ft1k M | tensorflow-ic-efficientnet-v2-imagenet21k-ft1k-m | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | R-CNN Resnet V2 mais rápido 1024x1024 | tensorflow-od-faster-rcnn-inception-resnet-v2-1024x1024-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | R-CNN Resnet-101 V1 640x640 mais rápido | tensorflow-od-faster-rcnn-resnet101-v1-640x640-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | R-CNN Resnet-50 V1 mais rápido 1024x1024 | tensorflow-od-faster-rcnn-resnet50-v1-1024x1024-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | R-CNN Resnet-50 V1 640x640 mais rápido | tensorflow-od-faster-rcnn-resnet50-v1-640x640-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | R-CNN Resnet-50 V1 800x1333 mais rápido | tensorflow-od-faster-rcnn-resnet50-v1-800x1333-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | BABADO | tensorflow-audioembedding-frill-1 | Classificação de áudio | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Classificação de imagens | tensorflow-ic-swin-base-patch4-window7-224 | Classificação de imagens | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | Incorporação de imagens | tensorflow-icembedding-imagenet-mobilenet-v2-100-224-fv-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Inception V3 | tensorflow-ic-imagenet-inception-v3-classification-4 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | Vetor de recursos de visualização do Inception V3 | tensorflow-icembedding-tf2-preview-inception-v3-fv-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | MobileNet V2 | tensorflow-ic-tf2-preview-mobilenet-v2-classification-4 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | MobileNet V2 0,35 128 | tensorflow-ic-imagenet-mobilenet-v2-035-128 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | MobileNet V2 0.50 224 | tensorflow-icembedding-imagenet-mobilenet-v2-050-224-fv-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | MobileNet V2 1.0 224 | tensorflow-ic-imagenet-mobilenet-v2-100-224-classification-4 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | MobileNet V2 1.40 224 | tensorflow-ic-imagenet-mobilenet-v2-140-224-classification-4 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | MobileNet Vetor de características V2 | tensorflow-icembedding-tf2-preview-mobilenet-v2-fv-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | MobileNet Vetor de características V2 | tensorflow-icembedding-tf2-preview-mobilenet-v2-featurevector-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | MobileNet V3 Grande 1.00 224 | tensorflow-ic-imagenet-mobilenet-v3-large-100-224 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | MobileNet V3 Pequeno 0,75 224 | tensorflow-ic-imagenet-mobilenet-v3-small-075-224 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | MobileNet V3 Pequeno 1.00 224 | tensorflow-ic-imagenet-mobilenet-v3-small-100-224 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | Detecção de objetos | tensorflow-od1-ssd-resnet50-v1-fpn-640x640-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | ResNet 50 | tensorflow-ic-resnet-50-classification-1 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.9xlarge, ml.g4dn.8xlarge, ml.p3.8xlarge | | Tensorflow | ResNet Vetor de 50 características | tensorflow-icembedding-resnet-50-featurevector-1 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | ResNet V1 50 | tensorflow-ic-imagenet-resnet-v1-50-classification-4 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | ResNet Vetor de características V2 152 | tensorflow-icembedding-imagenet-resnet-v2-152-featurevector-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | ResNet V2 50 | tensorflow-ic-imagenet-resnet-v2-50-classification-4 | Classificação de imagens | Apache-2.0 | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | ResNet Vetor de características V2 50 | tensorflow-icembedding-imagenet-resnet-v2-50-featurevector-4 | Classificação de imagens | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Retinanet 640x640 Resnet-101 | tensorflow-od-retinanet-resnet101-v1-fpn-640x640-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | BERT pequeno L-10 \_ H-512 \_ A-8 | tensorflow-tc-small-bert-bert-en-uncased-L-10-H-512-A-8 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT pequeno L-12 \_ H-256 \_ A-4 | tensorflow-tc-small-bert-bert-en-uncased-L-12-H-256-A-4 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT pequeno L-12 \_ H-768 \_ A-12 | tensorflow-tc-small-bert-bert-en-uncased-L-12-H-768-A-12 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT pequeno L-2 \_ H-128 \_ A-2 | tensorflow-tc-small-bert-bert-en-uncased-L-2-H-128-A-2 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT pequeno L-4 \_ H-512 \_ A-8 | tensorflow-tc-small-bert-bert-en-uncased-L-4-H-512-A-8 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT pequeno L-6 \_ H-768 \_ A-12 | tensorflow-tc-small-bert-bert-en-uncased-L-6-H-768-A-12 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | BERT pequeno L-8 \_ H-768 \_ A-12 | tensorflow-tc-small-bert-bert-en-uncased-L-8-H-768-A-12 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | SSD ResNet 152 V1 VPN 1024x1024 COCO '17 | tensorflow-od1-ssd-resnet152-v1-fpn-1024x1024-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD D0 EfficientDet | tensorflow-od-efficientdet-d0-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Efficientet E0 512x512 COCO '17 | tensorflow-od1-ssd-efficientdet-d0-512x512-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Efficientet E1 640x640 COCO '17 | tensorflow-od1-ssd-efficientdet-d1-640x640-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD D2 EfficientDet | tensorflow-od-efficientdet-d2-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Efficientet E2 768x768 COCO '17 | tensorflow-od1-ssd-efficientdet-d2-768x768-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD 3D EfficientDet | tensorflow-od-efficientdet-d3-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Efficientet E3 896x896 COCO '17 | tensorflow-od1-ssd-efficientdet-d3-896x896-coco17-tpu-32 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD D5 EfficientDet | tensorflow-od-efficientdet-d5-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Mobilenet V1 VPN 640x640 COCO '17 | tensorflow-od1-ssd-mobilenet-v1-fpn-640x640-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Mobilenet V2 | tensorflow-od-ssd-mobilenet-v2-2 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Mobilenet V2 640x640 | tensorflow-od-ssd-mobilenet-v2-fpnlite-640x640-1 | Detecção de objetos | apache-2.0 | Não | ml.g4dn.xlarge, ml.g5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Mobilenet FPN-Lite V2 320x320 COCO '17 | tensorflow-od1-ssd-mobilenet-v2-fpnlite-320x320-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD Mobilenet FPN-lite V2 640x640 COCO '17 | tensorflow-od1-ssd-mobilenet-v2-fpnlite-640x640-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD ResNet 101 V1 VPN 1024x1024 COCO '17 | tensorflow-od1-ssd-resnet101-v1-fpn-1024x1024-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD ResNet 101 V1 VPN 640x640 COCO '17 | tensorflow-od1-ssd-resnet101-v1-fpn-640x640-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD ResNet 152 V1 VPN 640x640 COCO '17 | tensorflow-od1-ssd-resnet152-v1-fpn-640x640-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | SSD ResNet 50 V1 VPN 1024x1024 COCO '17 | tensorflow-od1-ssd-resnet50-v1-fpn-1024x1024-coco17-tpu-8 | Detecção de objetos | apache-2.0 | Sim | ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Swin Base 4 12 384 | tensorflow-ic-swin-base-patch4-window12-384 | Classificação de imagens | mit | Sim | ml.c5.2xlarge, ml.c5.xlarge, ml.c6i.large, ml.c6i.xlarge, ml.g4dn.xlarge, ml.m4.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge, ml.r5.xlarge, ml.r5.xlarge | | Tensorflow | Base Talking Heads | tensorflow-tc-talking-heads-large | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | Classificação de texto | tensorflow-tc-bert-en-uncased-L-12-H-768-A-12-2 | Classificação de texto | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.xlarge, ml.g5.xlarge, ml.m5.12xlarge, ml.m5,24xgrande, ml.m5,2xgrande, ml.m5,4xgrande, ml.m5.xgrande, ml.p3,16xgrande, ml.p3,2xgrande, ml.p3,8xgrande | | Tensorflow | Incorporação de texto | tensorflow-tcembedding-universal-sentc-encoder-cmlm-en-large-1 | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | TRILL Destilado | tensorflow-audioembedding-trill-distilled-3 | Classificação de áudio | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Trillsson 1 | tensorflow-audioembedding-trillsson1-1 | Classificação de áudio | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Trillsson 2 | tensorflow-audioembedding-trillsson2-1 | Classificação de áudio | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Trillson 3 | tensorflow-audioembedding-trillsson3-1 | Classificação de áudio | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | | Tensorflow | Codificador de frases universal CMLM Base | tensorflow-tcembedding-universal-sentc-encoder-cmlm-en-base-1 | Incorporação de texto | apache-2.0 | Não | ml.c5.2xlarge, ml.c5.xlarge, ml.g4dn.xlarge, ml.m5.large, ml.m5.xlarge, ml.p3.2xlarge | ------ #### [ Classic ML Algorithms (11) ] SageMaker JumpStart A Amazon fornece implementações prontas para uso de algoritmos clássicos de aprendizado de máquina para tarefas de dados tabulares, como classificação, regressão e previsão de séries temporais. Esses algoritmos (XGBoost,LightGBM,CatBoost,scikit-learn,AutoGluon) são otimizados para dados estruturados e podem ser treinados do zero em seus próprios conjuntos de dados. | Fornecedor | Nome do modelo | ID do modelo | Tarefa | Licença | Fine-tunable | Tipos de instância de inferência compatíveis | | --- | --- | --- | --- | --- | --- | --- | | Autógluon | AutoGluon Classificação tabular | autogluon-classification-ensemble | Classificação tabular | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.p3.2xlarge | | Autógluon | AutoGluon Regressão tabular | autogluon-regression-ensemble | Regressão tabular | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.p3.2xlarge | | Cat boost | CatBoost Classificação | catboost-classification-model | Classificação tabular | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m4.16xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge | | Cat boost | CatBoost Regressão | catboost-regression-model | Regressão tabular | apache-2.0 | Sim | ml.c4.8xlarge, ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge | | Light gbm | Classificação LightGBM | lightgbm-classification-model | Classificação tabular | mit | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m4.16xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge | | Light gbm | Regressão LightGBM | lightgbm-regression-model | Regressão tabular | mit | Sim | ml.c4.8xlarge, ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge | | Maçarico | TabTransformer Classificação | pytorch-tabtransformerclassification-model | Classificação tabular | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.p3.2xlarge | | Maçarico | TabTransformer Regressão | pytorch-tabtransformerregression-model | Regressão tabular | apache-2.0 | Sim | ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.g4dn.xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.p3.2xlarge | | Sklearn | Classificação linear | sklearn-classification-linear | Classificação tabular | cláusula bsd-3 | Sim | ml.c4.8xlarge, ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.xlarge | | Xgboost | Classificação XGBoost | xgboost-classification-model | Classificação tabular | apache-2.0 | Sim | ml.c4.8xlarge, ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.xlarge | | Xgboost | Regressão XGBoost | xgboost-regression-model | Regressão tabular | apache-2.0 | Sim | ml.c4.8xlarge, ml.c5.18xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.xlarge | ------ **nota** Para obter as informações de licenciamento mais precisas e atualizadas, consulte a página de detalhes do modelo no SageMaker Studio ou a página do Hugging Face modelo.