Update Model
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Base model details. Required if kind is HF_BASE_MODEL. Must not be set otherwise.
The maximum context length supported by the model.
If set, the Chat Completions API will be enabled for this model.
The default draft model to use when creating a deployment. If empty, speculative decoding is disabled by default.
The default draft token count to use when creating a deployment. Must be specified if default_draft_model is specified.
If specified, this is the date when the serverless deployment of the model will be taken down.
The description of the model. Must be fewer than 1000 characters long.
Human-readable display name of the model. e.g. "My Model" Must be fewer than 64 characters long.
The URL to GitHub repository of the model.
The URL to the Hugging Face model.
The kind of model. If not specified, the default is HF_PEFT_ADDON.
KIND_UNSPECIFIED, HF_BASE_MODEL, HF_PEFT_ADDON, HF_TEFT_ADDON, FLUMINA_BASE_MODEL, FLUMINA_ADDON, DRAFT_ADDON, FIRE_AGENT PEFT addon details. Required if kind is HF_PEFT_ADDON or HF_TEFT_ADDON.
If true, the model will be publicly readable.
The state of the model.
STATE_UNSPECIFIED, UPLOADING, READY Contains detailed message when the last model operation fails.
If set, images can be provided as input to the model.
If set, tools (i.e. functions) can be provided as input to the model, and the model may respond with one or more tool calls.
TEFT addon details. Required if kind is HF_TEFT_ADDON. Must not be set otherwise.
Response
Base model details. Required if kind is HF_BASE_MODEL. Must not be set otherwise.
If true, the model is calibrated and can be deployed to non-FP16 precisions.
The resource name of the BYOC cluster to which this model belongs. e.g. accounts/my-account/clusters/my-cluster. Empty if it belongs to a Fireworks cluster.
The maximum context length supported by the model.
If set, the Chat Completions API will be enabled for this model.
The email address of the user who created this model.
The creation time of the model.
The default draft model to use when creating a deployment. If empty, speculative decoding is disabled by default.
The default draft token count to use when creating a deployment. Must be specified if default_draft_model is specified.
Populated from GetModel API call only.
If specified, this is the date when the serverless deployment of the model will be taken down.
The description of the model. Must be fewer than 1000 characters long.
Human-readable display name of the model. e.g. "My Model" Must be fewer than 64 characters long.
If the model was created from a fine-tuning job, this is the fine-tuning job name.
The URL to GitHub repository of the model.
The URL to the Hugging Face model.
The name of the the model from which this was imported. This field is empty if the model was not imported.
The kind of model. If not specified, the default is HF_PEFT_ADDON.
KIND_UNSPECIFIED, HF_BASE_MODEL, HF_PEFT_ADDON, HF_TEFT_ADDON, FLUMINA_BASE_MODEL, FLUMINA_ADDON, DRAFT_ADDON, FIRE_AGENT PEFT addon details. Required if kind is HF_PEFT_ADDON or HF_TEFT_ADDON.
PRECISION_UNSPECIFIED, FP16, FP8, FP8_MM, FP8_AR, FP8_MM_KV_ATTN, FP8_KV, FP8_MM_V2, FP8_V2, FP8_MM_KV_ATTN_V2 If true, the model will be publicly readable.
The state of the model.
STATE_UNSPECIFIED, UPLOADING, READY Contains detailed message when the last model operation fails.
If set, images can be provided as input to the model.
If set, tools (i.e. functions) can be provided as input to the model, and the model may respond with one or more tool calls.
TEFT addon details. Required if kind is HF_TEFT_ADDON. Must not be set otherwise.
Was this page helpful?