Enum Class OllamaModel
- All Implemented Interfaces:
Serializable,Comparable<OllamaModel>,Constable,ChatModelDescription,ModelDescription
Helper class for common Ollama models.
- Since:
- 1.0.0
- Author:
- Siarhei Blashuk, Thomas Vitale
-
Nested Class Summary
Nested classes/interfaces inherited from class java.lang.Enum
Enum.EnumDesc<E extends Enum<E>> -
Enum Constant Summary
Enum ConstantsEnum ConstantDescriptionCode Llama is based on Llama 2 modelThe 2.7B uncensored Dolphin modelGemma is a lightweight model with 2 billion and 7 billionThe current, most capable model that runs on a single GPU.Llama 2 is a collection of language models ranging from 7B to 70B parameters.Uncensored Llama 2 modelLlama 3 is a collection of language models ranging from 8B and 70B parameters.The 8B language model from Meta.The Llama 3.2 3B language model from Meta.The Llama 3.2 1B language model from Meta.The Llama 3.2 3B language model from Meta.The Llama 3.2 Vision 11B language model from Meta.The Llama 3.2 Vision 90B language model from Meta.Llava is a Large Language and Vision Assistant modelThe 7B parameters modelA 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.A small vision language model designed to run efficiently on edge devices.State-of-the-art large embedding model from mixedbread.aiA fine-tuned Mistral modelA high-performing open embedding model with a large token context window.Orca Mini is based on Llama and Llama 2 ranging from 3 billion parameters to 70 billionThe Phi-2 2.7B language modelThe Phi-3 3.8B language modelQwen 2.5Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.Qwen3 4BQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.QwQ is the reasoning model of the Qwen series.Starling-7B model -
Method Summary
Modifier and TypeMethodDescriptiongetName()Returns the name of the model.id()static OllamaModelReturns the enum constant of this class with the specified name.static OllamaModel[]values()Returns an array containing the constants of this enum class, in the order they are declared.Methods inherited from class java.lang.Enum
clone, compareTo, describeConstable, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOfMethods inherited from interface org.springframework.ai.model.ModelDescription
getDescription, getVersion
-
Enum Constant Details
-
QWEN_2_5_3B
-
QWEN_2_5_7B
Qwen 2.5 -
QWEN2_5_VL
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. -
QWEN3_7B
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. -
QWEN3_4B
Qwen3 4B -
QWQ
QwQ is the reasoning model of the Qwen series. -
LLAMA2
Llama 2 is a collection of language models ranging from 7B to 70B parameters. -
LLAMA3
Llama 3 is a collection of language models ranging from 8B and 70B parameters. -
LLAMA3_1
The 8B language model from Meta. -
LLAMA3_2
The Llama 3.2 3B language model from Meta. -
LLAMA3_2_VISION_11b
The Llama 3.2 Vision 11B language model from Meta. -
LLAMA3_2_VISION_90b
The Llama 3.2 Vision 90B language model from Meta. -
LLAMA3_2_1B
The Llama 3.2 1B language model from Meta. -
LLAMA3_2_3B
The Llama 3.2 3B language model from Meta. -
MISTRAL
The 7B parameters model -
MISTRAL_NEMO
A 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA. -
MOONDREAM
A small vision language model designed to run efficiently on edge devices. -
DOLPHIN_PHI
The 2.7B uncensored Dolphin model -
PHI
The Phi-2 2.7B language model -
PHI3
The Phi-3 3.8B language model -
NEURAL_CHAT
A fine-tuned Mistral model -
STARLING_LM
Starling-7B model -
CODELLAMA
Code Llama is based on Llama 2 model -
ORCA_MINI
Orca Mini is based on Llama and Llama 2 ranging from 3 billion parameters to 70 billion -
LLAVA
Llava is a Large Language and Vision Assistant model -
GEMMA
Gemma is a lightweight model with 2 billion and 7 billion -
GEMMA3
The current, most capable model that runs on a single GPU. -
LLAMA2_UNCENSORED
Uncensored Llama 2 model -
NOMIC_EMBED_TEXT
A high-performing open embedding model with a large token context window. -
MXBAI_EMBED_LARGE
State-of-the-art large embedding model from mixedbread.ai
-
-
Method Details
-
values
Returns an array containing the constants of this enum class, in the order they are declared.- Returns:
- an array containing the constants of this enum class, in the order they are declared
-
valueOf
Returns the enum constant of this class with the specified name. The string must match exactly an identifier used to declare an enum constant in this class. (Extraneous whitespace characters are not permitted.)- Parameters:
name- the name of the enum constant to be returned.- Returns:
- the enum constant with the specified name
- Throws:
IllegalArgumentException- if this enum class has no constant with the specified nameNullPointerException- if the argument is null
-
id
-
getName
Description copied from interface:ModelDescriptionReturns the name of the model.- Specified by:
getNamein interfaceModelDescription- Returns:
- the name of the model
-