Available foundation models
Amazon SageMaker JumpStart offers state-of-the-art, built-in publicly available and proprietary foundation models to customize and integrate into your generative AI workflows.
Publicly available foundation models
Amazon SageMaker JumpStart onboards and maintains open source foundation models from third-party sources. To get started with one of these publicly available models, see JumpStart foundation model usage or explore one of the available Example notebooks. In a given example notebook for a publicly available model, try switching out the model ID to experiment with different models within the same model family.
For more information on model IDs and resources on deploying publicly available JumpStart foundation models with the SageMaker Python SDK, see Use foundation models with the SageMaker Python SDK.
By definition, foundation models are adaptable to many downstream tasks. Foundation models are trained on massive amounts of general domain data and the same model can be implemented or customized for multiple use cases. When choosing your foundation model, start with defining a specific task, such as text generation or image generation.
Publicly available time series forecasting models
Time series forecasting models are designed to analyze and make predictions on sequential data over time. These models can be applied to various domains such as finance, weather forecasting, or energy demand forecasting. The Chronos models are tailored for time series forecasting tasks, enabling accurate predictions based on historical data patterns.
| Model Name | Model ID | Model Source | Fine-tunable |
|---|---|---|---|
Chronos T5 Small |
autogluon-forecasting-chronos-t5-small |
Amazon |
No |
Chronos T5 Base |
autogluon-forecasting-chronos-t5-base |
Amazon |
No |
Chronos T5 Large |
autogluon-forecasting-chronos-t5-large |
Amazon |
No |
Publicly available text generation models
Text generation foundation models can be used for a variety of downstream tasks, including text summarization, text classification, question answering, long-form content generation, short-form copywriting, information extraction, and more.
| Model Name | Model ID | Model Source | Fine-tunable |
|---|---|---|---|
Alexa TM 20B |
pytorch-textgeneration1-alexa20b |
Amazon |
No |
Bloom 1b1 |
huggingface-textgeneration-bloom-1b1 |
Hugging Face |
No |
Bloom 1b7 |
huggingface-textgeneration-bloom-1b7 |
Hugging Face |
No |
Bloom 3B |
huggingface-textgeneration1-bloom-3b |
Hugging Face |
Yes |
Bloom 560m |
huggingface-textgeneration-bloom-560m |
Hugging Face |
No |
Bloom 7B1 |
huggingface-textgeneration1-bloom-7b1 |
Hugging Face |
Yes |
Bloomz 1b1 |
huggingface-textgeneration-bloomz-1b1 |
Hugging Face |
No |
Bloomz 1b7 |
huggingface-textgeneration-bloomz-1b7 |
Hugging Face |
No |
BloomZ 3B FP16 |
huggingface-textgeneration1-bloom-3b-fp16 |
Hugging Face |
Yes |
Bloomz 560m |
huggingface-textgeneration-bloomz-560m |
Hugging Face |
No |
BloomZ 7B1 FP16 |
huggingface-textgeneration1-bloomz-7b1-fp16 |
Hugging Face |
Yes |
Code Llama 13B |
meta-textgeneration-llama-codellama-13b |
Meta |
Yes |
Code Llama 13B Instruct |
meta-textgeneration-llama-codellama-13b-instruct |
Meta |
No |
Code Llama 13B Python |
meta-textgeneration-llama-codellama-13b-python |
Meta |
Yes |
Code Llama 34B |
meta-textgeneration-llama-codellama-34b |
Meta |
Yes |
Code Llama 34B Instruct |
meta-textgeneration-llama-codellama-34b-instruct |
Meta |
No |
Code Llama 34B Python |
meta-textgeneration-llama-codellama-34b-python |
Meta |
Yes |
Code Llama 70B |
meta-textgeneration-llama-codellama-70b |
Meta |
Yes |
Code Llama 70B Instruct |
meta-textgeneration-llama-codellama-70b-instruct |
Meta |
No |
Code Llama 70B Python |
meta-textgeneration-llama-codellama-70b-python |
Meta |
Yes |
Code Llama 7B |
meta-textgeneration-llama-codellama-7b |
Meta |
Yes |
Code Llama 7B Instruct |
meta-textgeneration-llama-codellama-7b-instruct |
Meta |
No |
Code Llama 7B Python |
meta-textgeneration-llama-codellama-7b-python |
Meta |
Yes |
CyberAgentLM2-7B-Chat (CALM2-7B-Chat) |
huggingface-llm-calm2-7b-chat-bf16 |
Hugging Face |
Yes |
DistilGPT2 |
huggingface-textgeneration-distilgpt2 |
Hugging Face |
No |
Dolly V2 12b BF16 |
huggingface-textgeneration-dolly-v2-12b-bf16 |
Hugging Face |
No |
Dolly V2 3b BF16 |
huggingface-textgeneration-dolly-v2-3b-bf16 |
Hugging Face |
No |
Dolly V2 7b BF16 |
huggingface-textgeneration-dolly-v2-7b-bf16 |
Hugging Face |
No |
Dolphin 2.2.1 Mistral 7B |
huggingface-llm-dolphin-2-2-1-mistral-7b |
Hugging Face |
No |
Dolphin 2.5 Mixtral 8 7B |
huggingface-llm-dolphin-2-5-mixtral-8x7b |
Hugging Face |
No |
Dolphin 2.7 Mixtral 8 7B |
huggingface-llm-dolphin-2-7-mixtral-8x7b |
Hugging Face |
No |
EleutherAI GPT Neo 2.7B |
huggingface-llm-eleutherai-gpt-neo-1-3b |
Hugging Face |
No |
EleutherAI GPT Neo 2.7B |
huggingface-llm-eleutherai-gpt-neo-2-7b |
Hugging Face |
No |
Falcon 180B BF16 |
huggingface-llm-falcon-180b-bf16 |
Hugging Face |
No |
Falcon 180B Chat BF16 |
huggingface-llm-falcon-180b-chat-bf16 |
Hugging Face |
No |
Falcon 40B BF16 |
huggingface-llm-falcon-40b-bf16 |
Hugging Face |
Yes |
Falcon 40B Instruct BF16 |
huggingface-llm-falcon-40b-instruct-bf16 |
Hugging Face |
Yes |
Falcon 7B BF16 |
huggingface-llm-falcon-7b-bf16 |
Hugging Face |
Yes |
Falcon 7B Instruct BF16 |
huggingface-llm-falcon-7b-instruct-bf16 |
Hugging Face |
Yes |
Falcon Lite |
huggingface-llm-amazon-falconlite |
Hugging Face |
No |
Falcon Lite 2 |
huggingface-llm-amazon-falconlite2 |
Hugging Face |
No |
Falcon RW 1B |
huggingface-llm-tiiuae-falcon-rw-1b |
Hugging Face |
No |
Flan-T5 Base |
huggingface-text2text-flan-t5-base |
Hugging Face |
Yes |
Flan-T5 Base Model Fine-tuned on the Samsum Dataset |
huggingface-text2text-flan-t5-base-samsum |
Hugging Face |
No |
Flan-T5 Large |
huggingface-text2text-flan-t5-large |
Hugging Face |
Yes |
Flan-T5 Small |
huggingface-text2text-flan-t5-small |
Hugging Face |
Yes |
Flan-T5 XL |
huggingface-text2text-flan-t5-xl |
Hugging Face |
Yes |
Flan-T5 XXL |
huggingface-text2text-flan-t5-xxl |
Hugging Face |
Yes |
Flan-UL2 BF16 |
huggingface-text2text-flan-ul2-bf16 |
Hugging Face |
No |
Gemma 2B |
huggingface-llm-gemma-2b |
Hugging Face |
Yes |
Gemma 2B Instruct |
huggingface-llm-gemma-2b-instruct |
Hugging Face |
Yes |
Gemma 7B |
huggingface-llm-gemma-7b |
Hugging Face |
Yes |
Gemma 7B Instruct |
huggingface-llm-gemma-7b-instruct |
Hugging Face |
Yes |
GPT 2 |
huggingface-textgeneration-gpt2 |
Hugging Face |
No |
GPT NeoX 20B FP16 |
huggingface-textgeneration2-gpt-neox-20b-fp16 |
Hugging Face |
No |
GPT NeoXT Chat Base 20B FP16 |
huggingface-textgeneration2-gpt-neoxt-chat-base-20b-fp16 |
Hugging Face |
No |
GPT-2 XL |
huggingface-textgeneration1-gpt-2-xl |
Hugging Face |
Yes |
GPT-J 6B |
huggingface-textgeneration1-gpt-j-6b |
Hugging Face |
Yes |
GPT-Neo 1.3B |
huggingface-textgeneration1-gpt-neo-1-3b |
Hugging Face |
Yes |
GPT-Neo 125M |
huggingface-textgeneration1-gpt-neo-125m |
Hugging Face |
Yes |
GPT-NEO 2.7B |
huggingface-textgeneration1-gpt-neo-2-7b |
Hugging Face |
Yes |
Japanese StableLM Instruct Alpha 7B v2 |
model-textgenerationjp-japanese-stablelm-instruct-alpha-7b-v2 |
Hugging Face |
No |
LightGPT Instruct 6B |
huggingface-textgeneration1-lightgpt |
Hugging Face |
Yes |
Lite Llama 460M 1T |
huggingface-llm-ahxt-litellama-460m-1t |
Hugging Face |
No |
Llama 2 13B |
meta-textgeneration-llama-2-13b |
Meta |
Yes |
Llama 2 13B Chat |
meta-textgeneration-llama-2-13b-f |
Meta |
Yes |
Llama 2 13B Chat Neuron |
meta-textgenerationneuron-llama-2-13b-f |
Meta |
No |
Llama 2 13B Neuron |
meta-textgenerationneuron-llama-2-13b |
Meta |
Yes |
Llama 2 70B |
meta-textgeneration-llama-2-70b |
Meta |
Yes |
Llama 2 70B Chat |
meta-textgeneration-llama-2-70b-f |
Meta |
Yes |
Llama 2 70B Chat Neuron |
meta-textgenerationneuron-llama-2-70b-f |
Meta |
No |
Llama 2 70B Neuron |
meta-textgenerationneuron-llama-2-70b |
Meta |
No |
Llama 2 7B |
meta-textgeneration-llama-2-7b |
Meta |
Yes |
Llama 2 7B Chat |
meta-textgeneration-llama-2-7b-f |
Meta |
Yes |
Llama 2 7B Chat Neuron |
meta-textgenerationneuron-llama-2-7b-f |
Meta |
No |
Llama 2 7B Neuron |
meta-textgenerationneuron-llama-2-7b |
Meta |
Yes |
Llama 3 8B |
meta-textgeneration-llama-3-8b |
Meta |
Yes |
Llama 3 8B Instruct |
meta-textgeneration-llama-3-8b-instruct |
Meta |
Yes |
Llama 3 70B |
meta-textgeneration-llama-3-70b |
Meta |
Yes |
Llama 3 70B Instruct |
meta-textgeneration-llama-3-70b-instruct |
Meta |
Yes |
Llama Guard 7B |
meta-textgeneration-llama-guard-7b |
Meta |
No |
Mistral 7B |
huggingface-llm-mistral-7b |
Hugging Face |
Yes |
Mistral 7B Instruct |
huggingface-llm-mistral-7b-instruct |
Hugging Face |
No |
Mistral 7B OpenOrca AWQ |
huggingface-llm-thebloke-mistral-7b-openorca-awq |
Hugging Face |
No |
Mistral 7B SFT Alpha |
huggingface-llm-huggingfaceh4-mistral-7b-sft-alpha |
Hugging Face |
No |
Mistral 7B SFT Beta |
huggingface-llm-huggingfaceh4-mistral-7b-sft-beta |
Hugging Face |
No |
Mistral Lite |
huggingface-llm-amazon-mistrallite |
Hugging Face |
No |
Mistral Trix V1 |
huggingface-llm-cultrix-mistraltrix-v1 |
Hugging Face |
No |
Mixtral 8x7B |
huggingface-llm-mixtral-8x7b |
Hugging Face |
Yes |
Mixtral 8x7B Instruct |
huggingface-llm-mixtral-8x7b-instruct |
Hugging Face |
Yes |
MPT 7B BF16 |
huggingface-textgeneration1-mpt-7b-bf16 |
Hugging Face |
No |
MPT 7B Instruct BF16 |
huggingface-textgeneration1-mpt-7b-instruct-bf16 |
Hugging Face |
No |
MPT 7B StoryWriter-65k+ BF16 |
huggingface-textgeneration1-mpt-7b-storywriter-bf16 |
Hugging Face |
No |
Multilingual GPT |
huggingface-llm-ai-forever-mgpt |
Hugging Face |
No |
Nous Hermes 2 SOLAR 10.7B |
huggingface-llm-nousresearch-nous-hermes-2-solar-10-7b |
Hugging Face |
No |
Nous Hermes Llama 2 13B |
huggingface-llm-nousresearch-nous-hermes-llama2-13b |
Hugging Face |
No |
Nous Hermes Llama 2 7B |
huggingface-llm-nousresearch-nous-hermes-llama-2-7b |
Hugging Face |
No |
Open Hermes 2 Mistral 7B |
huggingface-llm-teknium-openhermes-2-mistral-7b |
Hugging Face |
No |
Open LlaMa |
huggingface-textgeneration-open-llama |
Hugging Face |
No |
Open Llama 7B V2 |
huggingface-llm-openlm-research-open-llama-7b-v2 |
Hugging Face |
No |
Platypus 2 7B |
huggingface-llm-garage-baind-platypus2-7b |
Hugging Face |
No |
Pythia 160m Deduped |
huggingface-llm-eleutherai-pythia-160m-deduped |
Hugging Face |
No |
Pythia 7m Deduped |
huggingface-llm-eleutherai-pythia-70m-deduped |
Hugging Face |
No |
Quality Controlled Paraphrase Generation |
huggingface-text2text-qcpg-sentences |
Hugging Face |
No |
RedPajama INCITE Base 3B V1 |
huggingface-textgeneration1-redpajama-incite-base-3B-v1-fp16 |
Hugging Face |
Yes |
RedPajama INCITE Base 7B V1 |
huggingface-textgeneration1-redpajama-incite-base-7B-v1-fp16 |
Hugging Face |
Yes |
RedPajama INCITE Chat 3B V1 |
huggingface-textgeneration1-redpajama-incite-chat-3B-v1-fp16 |
Hugging Face |
Yes |
RedPajama INCITE Chat 7B V1 |
huggingface-textgeneration1-redpajama-incite-chat-7B-v1-fp16 |
Hugging Face |
Yes |
RedPajama INCITE Instruct 3B V1 |
huggingface-textgeneration1-redpajama-incite-instruct-3B-v1-fp16 |
Hugging Face |
Yes |
RedPajama INCITE Instruct 7B V1 |
huggingface-textgeneration1-redpajama-incite-instruct-7B-v1-fp16 |
Hugging Face |
Yes |
Rinna Bilingual GPT NeoX 4B Instruction PPO |
huggingface-llm-bilingual-rinna-4b-instruction-ppo-bf16 |
Hugging Face |
No |
Rinna Japanese GPT NeoX 3.6B Instruction PPO |
huggingface-llm-rinna-3-6b-instruction-ppo-bf16 |
Hugging Face |
No |
Star Chat Alpha |
huggingface-llm-huggingfaceh4-starchat-alpha |
Hugging Face |
No |
Star Chat Beta |
huggingface-llm-huggingfaceh4-starchat-beta |
Hugging Face |
No |
StarCoder |
huggingface-llm-starcoder |
Hugging Face |
No |
StarCoderBase |
huggingface-llm-starcoderbase |
Hugging Face |
No |
T0pp |
huggingface-text2text-bigscience-t0pp |
Hugging Face |
No |
T5 One Line Summary |
huggingface-text2text-t5-one-line-summary |
Hugging Face |
No |
Tiny Llama 1.1B |
huggingface-llm-tinyllama-1-1b-intermediate-step-1431k-3 |
Hugging Face |
No |
Tiny Llama 1.1B Chat V0.6 |
huggingface-llm-tinyllama-tinyllama-1-1b-chat-v0-6 |
Hugging Face |
No |
Tiny Llama 1.1B Chat V1 |
huggingface-llm-tinyllama-tinyllama-1-1b-chat-v1-0 |
Hugging Face |
No |
Writer Palmyra Small |
huggingface-llm-writer-palmyra-small |
Hugging Face |
No |
YARN Mistral 7B 128k |
huggingface-llm-nousresearch-yarn-mistral-7b-128k |
Hugging Face |
No |
Zephyr 7B Alpha |
huggingface-llm-huggingfaceh4-zephyr-7b-alpha |
Hugging Face |
No |
Zephyr 7B Beta |
huggingface-llm-huggingfaceh4-zephyr-7b-beta |
Hugging Face |
No |
To explore the latest text generation JumpStart foundation models, use the
Text Generation filter on the Getting started with Amazon SageMaker JumpStart
Publicly available image generation models
JumpStart provides a wide variety of Stable Diffusion image generation foundation models including base models from Stability AI as well as pre-trained models for specific text-to-image tasks from Hugging Face. If you need to fine-tune your text-to-image foundation model, you can use Stable Diffusion 2.1 base from Stability AI. If you want to explore models that are already trained on specific art styles, you can explore one of the many third-party models from Hugging Face directly in the Amazon SageMaker Studio UI or SageMaker AI Studio Classic UI.
To explore the latest image generation JumpStart foundation models, use the
Text to Image filter on the Getting started with Amazon SageMaker JumpStart
Proprietary foundation models
Amazon SageMaker JumpStart provides access to proprietary foundation models from third-party
providers such as AI21 Labs
To get started with one of these proprietary models, see JumpStart foundation model usage. To use a proprietary foundation model, you must first subscribe to the model in AWS Marketplace. After subscribing to the model, locate the foundation model in Studio or SageMaker Studio Classic. For more information, see SageMaker JumpStart pretrained models.
To explore the latest proprietary foundation models for a variety of use cases,
see Getting started with Amazon SageMaker JumpStart
