BaseModelInfoSchema
Whether this model can be used for fine-tuning jobs.
Whether this model can be deployed for inference.
Total batch size used during fine-tuning.
Number of gradient accumulation steps for fine-tuning.
Learning rate for fine-tuning.
Per-device micro-batch size for fine-tuning.
List of active deployment records associated with this model.
Human-readable name for the model shown in the UI.
Hugging Face repository identifier for this model.
Unique numeric identifier for the base model.
Canonical model identifier used in API requests.
Category of model. Common values: "language_model", "image_model".
Maximum context length (in tokens) supported by this model.
List of region identifiers where this model is available for deployment.
Estimated training time (in seconds) per log step, used for duration projections.
Y-intercept of the training time regression curve, used for fine-tuning duration estimates.
Maximum allowed size (in bytes) for a Hugging Face LoRA adapter when fine-tuning this model.
Cost in USD per million input tokens for inference.
Whether this model was imported by the user (third-party) rather than provided natively by Hyperstack.
Cost in USD per million output tokens for inference.
Estimated training cost per log step, used for fine-tuning cost projections.
Input modalities the model accepts, such as text and image. A model that lists image supports image-to-text input.
Output modalities the model produces, such as text.
{
"available_for_finetuning": true,
"available_for_inference": true,
"default_batch_size": "total",
"default_gradient_accumulation_steps": "number",
"default_lr": "learning",
"default_micro_batch_size": "per-device",
"deployment_records": [
null
],
"display_name": "string",
"hf_repo": "string",
"model_id": 0,
"model_name": "string",
"model_type": "string",
"supported_context_len": 0,
"supported_locations": [
"string"
],
"training_time_per_log": 0,
"training_time_y_intercept": 0,
"allowed_hf_lora_adapter_size": 0,
"input_token_cost_per_m": 0,
"is_third_party": true,
"output_token_cost_per_m": 0,
"training_cost_per_log": 0
}