開始使用 Amazon SageMaker JumpStart
概觀
Amazon SageMaker JumpStart 是機器學習 (ML) 中心,可協助您加速機器學習之旅。探索如何透過模型中心預先訓練的模型、預先訓練的基礎模型和預先建置的解決方案開始使用內建演算法,以解決常見使用案例。若要開始使用,請參閱可快速執行的文件或範例筆記本。
Total results: 567
- 熱門度
- 精選優先
- A-Z 型號名稱
- Z-A 型號名稱
-
foundation model
FeaturedText GenerationMeta-Llama-3-70B-Instruct
Meta70B instruction tuned variant of Llama 3 models. Llama 3 uses a decoder-only transformer architecture and new tokenizer that provides improved model performance.Fine-tunable -
foundation model
FeaturedText GenerationMeta-Llama-3.1-405B-FP8
Meta405B variant of Llama 3.1 models. Llama 3.1 uses a decoder-only transformer architecture and new tokenizer that provides improved model performance.Fine-tunable -
foundation model
FeaturedText GenerationMeta-Llama-3.1-8B-Instruct
Meta8B instruction tuned variant of Llama 3.1 models. Llama 3.1 uses a decoder-only transformer architecture and new tokenizer that provides improved model performance.Fine-tunable -
foundation model
FeaturedText GenerationMeta-Llama-3.1-70B-Instruct
Meta70B instruction tuned variant of Llama 3.1 models. Llama 3.1 uses a decoder-only transformer architecture and new tokenizer that provides improved model performance.Fine-tunable -
foundation model
FeaturedText GenerationMeta Llama 3.2 3B Instruct
Meta3B instruction tuned variant of Llama 3.2 models. Llama 3.2 uses a decoder-only transformer architecture and new tokenizer that provides improved model performance.Fine-tunable -
foundation model
FeaturedText GenerationMeta Llama 3.2 1B Instruct
Meta1B instruction tuned variant of Llama 3.2 models. Llama 3.2 uses a decoder-only transformer architecture and new tokenizer that provides improved model performance.Fine-tunable -
foundation model
FeaturedVision LanguageMeta Llama 3.2 11B Vision Instruct
Meta11b instruction-tuned variants of Llama 3.2 models that supports both text and image as input.Deploy only -
foundation model
FeaturedText GenerationLlama 2 13B
Meta13B variant of Llama 2 models. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. Llama 2 is intended for commercial and research use in English. It comes in a range of parameter sizes—7 billion, 13 billion, and 70 billion—as well as pre-trained and fine-tuned variations.Fine-tunable -
foundation model
FeaturedText GenerationLlama 3
MetaLlama three from Meta comes in two parameter sizes — 8B and 70B with 8k context length — that can support a broad range of use cases with improvements in reasoning, code generation, and instruction following.
Deploy Only -
foundation model
FeaturedText GenerationLlama 2 70B
Meta70B variant of Llama 2 models. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. Llama 2 is intended for commercial and research use in English. It comes in a range of parameter sizes—7 billion, 13 billion, and 70 billion—as well as pre-trained and fine-tuned variations.Fine-tunable -
foundation model
FeaturedText GenerationLlama 2 7B
Meta7B variant of Llama 2 models. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. Llama 2 is intended for commercial and research use in English. It comes in a range of parameter sizes—7 billion, 13 billion, and 70 billion—as well as pre-trained and fine-tuned variations.Fine-tunable -
foundation model
FeaturedText GenerationLlama 2 70B Chat
Meta70B dialogue use case optimized variant of Llama 2 models. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. Llama 2 is intended for commercial and research use in English. It comes in a range of parameter sizes—7 billion, 13 billion, and 70 billion—as well as pre-trained and fine-tuned variations.Fine-tunable