jesterTOV.inference.config.schema.FlowMCSamplerConfig

class FlowMCSamplerConfig(**data)

Bases: BaseSamplerConfig

Configuration for FlowMC sampler (normalizing flow-enhanced MCMC).

Variables:

• type (Literal["flowmc"]) – Sampler type identifier

• n_chains (int) – Number of parallel chains

• n_loop_training (int) – Number of training loops

• n_loop_production (int) – Number of production loops

• n_local_steps (int) – Number of local MCMC steps per loop

• n_global_steps (int) – Number of global steps per loop

• n_epochs (int) – Number of training epochs for normalizing flow

• learning_rate (float) – Learning rate for flow training

• train_thinning (int) – Thinning factor for training samples (default: 1)

• output_thinning (int) – Thinning factor for output samples (default: 5)

• output_dir (str) – Directory to save results

• n_eos_samples (int) – Number of EOS samples to generate after inference (default: 10000)

__init__(**data)

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Methods

__init__(**data)	Create a new model by parsing and validating input data from keyword arguments.
construct([_fields_set])
copy(*[, include, exclude, update, deep])	Returns a copy of the model.
dict(*[, include, exclude, by_alias, ...])
from_orm(obj)
json(*[, include, exclude, by_alias, ...])
model_construct([_fields_set])	Creates a new instance of the Model class with validated data.
model_copy(*[, update, deep])	!!! abstract "Usage Documentation"
model_dump(*[, mode, include, exclude, ...])	!!! abstract "Usage Documentation"
model_dump_json(*[, indent, ensure_ascii, ...])	!!! abstract "Usage Documentation"
model_json_schema([by_alias, ref_template, ...])	Generates a JSON schema for a model class.
model_parametrized_name(params)	Compute the class name for parametrizations of generic classes.
model_post_init(context, /)	Override this method to perform additional initialization after __init__ and model_construct.
model_rebuild(*[, force, raise_errors, ...])	Try to rebuild the pydantic-core schema for the model.
model_validate(obj, *[, strict, extra, ...])	Validate a pydantic model instance.
model_validate_json(json_data, *[, strict, ...])	!!! abstract "Usage Documentation"
model_validate_strings(obj, *[, strict, ...])	Validate the given object with string data against the Pydantic model.
parse_file(path, *[, content_type, ...])
parse_obj(obj)
parse_raw(b, *[, content_type, encoding, ...])
schema([by_alias, ref_template])
schema_json(*[, by_alias, ref_template])
update_forward_refs(**localns)
validate(value)
validate_base_positive(v)	Validate that value is positive.
validate_positive(v)	Validate that value is positive.
validate_positive_float(v)	Validate that learning rate is positive.

Attributes

model_computed_fields
model_config	Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
model_extra	Get extra fields set during validation.
model_fields
model_fields_set	Returns the set of fields that have been explicitly set on this model instance.
type
n_chains
n_loop_training
n_loop_production
n_local_steps
n_global_steps
n_epochs
learning_rate
train_thinning
output_thinning
output_dir
n_eos_samples
log_prob_batch_size

learning_rate: float

model_config: ClassVar[ConfigDict] = {'extra': 'forbid'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

n_chains: int

n_epochs: int

n_global_steps: int

n_local_steps: int

n_loop_production: int

n_loop_training: int

output_thinning: int

train_thinning: int

type: Literal['flowmc']

classmethod validate_positive(v)

Validate that value is positive.

Return type:

int

classmethod validate_positive_float(v)

Validate that learning rate is positive.

Return type:

float