Foundation model IDs
When you work with watsonx.ai foundation models from a notebook in watsonx.ai, you can use the short names that are defined in the ModelTypes class of the Python library to refer to the supported foundation models.
from ibm_watsonx_ai.foundation_models.utils.enums import ModelTypes
model = Model(
model_id=ModelTypes.FLAN_UL2,...
)
Because the list of available foundation models changes frequently to support the latest models, short names for new models might not be available immediately.
You can also use the List the available foundation models REST method to get the {model_id}
for a foundation model, and then specify the model ID as a string in your code.
model = Model(
model_id="google/flan-ul2",...
)
Foundation model IDs for APIs
The following list shows the values to use in the {model_id}
parameter when you reference a foundation model from the API.
-
all-minilm-l12-v2
sentence-transformers/all-minilm-l12-v2
-
allam-1-13b-instruct
sdaia/allam-1-13b-instruct
-
bge-large-en-v1
baai/bge-large-en-v1
-
codellama-34b-instruct-hf
codellama/codellama-34b-instruct-hf
-
elyza-japanese-llama-2-7b-instruct
elyza/elyza-japanese-llama-2-7b-instruct
-
flan-t5-xxl-11b
google/flan-t5-xxl
-
flan-ul2-20b
google/flan-ul2
-
granite-8b-japanese
ibm/granite-8b-japanese
-
granite-13b-chat-v2
ibm/granite-13b-chat-v2
-
granite-13b-instruct-v2
ibm/granite-13b-instruct-v2
-
granite-20b-multilingual
ibm/granite-20b-multilingual
-
granite-3b-code-instruct
ibm/granite-3b-code-instruct
-
granite-8b-code-instruct
ibm/granite-8b-code-instruct
-
granite-20b-code-instruct
ibm/granite-20b-code-instruct
-
granite-34b-code-instruct
ibm/granite-34b-code-instruct
-
jais-13b-chat
core42/jais-13b-chat
-
llama-3-8b-instruct
meta-llama/llama-3-8b-instruct
-
llama-3-70b-instruct
meta-llama/llama-3-70b-instruct
-
llama-2-13b-chat
meta-llama/llama-2-13b-chat
-
llama-2-70b-chat
meta-llama/llama-2-70b-chat
-
llama2-13b-dpo-v7
mnci/llama2-13b-dpo-v7
-
merlinite-7b
ibm-mistralai/merlinite-7b
-
mixtral-8x7b-instruct-v01
mistralai/mixtral-8x7b-instruct-v01
-
mixtral-8x7b-instruct-v01-q
ibm-mistralai/mixtral-8x7b-instruct-v01-q
-
mt0-xxl-13b
bigscience/mt0-xxl
-
multilingual-e5-large
intfloat/multilingual-e5-large
Parent topic: Coding generative AI solutions