Overview
Target configuration controls stimulus and rollout generation behavior. Targets are composed from a base template plus per-target overrides.
Configuration Fields
Generators
List of generator configurations. See Generators."generators": [
{"type": "oneshot_qs", "model": "claude-sonnet-4-5-20250929", "numq": 10},
{"type": "hardcoded", "numq": 2, "questions": ["Question 1", "Question 2"]}
]
Prompts
Teacher prompt name - defines the expert behavior to bake into the model"teacher_prompt": "expert_python_developer"
Student prompt name - what the model receives at inference time"student_prompt": "simple_coding_assistant"
# Or "" for empty (always-on behavior)
Use empty student_prompt ("") to permanently bake behavior into the model without needing any prompt trigger at inference time. This is the ultimate proof that baking modifies model weights!
Deprecated Fields: The u and v fields are deprecated in favor of teacher_prompt and student_prompt. Please update your code to use the new field names. The deprecated fields will be removed in a future version.
Model Configuration
Base model for rollout generation. Required for rollout jobs."model_name": "Qwen/Qwen3-32B"
Generation Parameters
Maximum tokens to generate per response Generation temperature (0.0-2.0). Higher = more random/creative. Number of trajectories (responses) to generate per stimulus"num_traj_per_stimulus": 5
Maximum concurrent API requests during rollout Advanced
Additional arguments passed to chat.completions.create()"extra_kwargs": {
"top_p": 0.9,
"frequency_penalty": 0.5
}
Complete Example
target = client.targets.set(
target_name="advanced_target",
repo_name="my_repo",
template="default",
overrides={
# Generators
"generators": [
{
"type": "oneshot_qs",
"model": "claude-sonnet-4-5-20250929",
"numq": 50,
"temperature": 1.2
},
{
"type": "from_dataset",
"dataset": "code_contests",
"numq": 30,
"seed": 42
}
],
# Prompts
"teacher_prompt": "system_prompt_expert",
"student_prompt": "user_prompt_detailed",
# Model
"model_name": "Qwen/Qwen3-32B",
# Generation params
"max_tokens": 200,
"temperature": 1.0,
"num_traj_per_stimulus": 3,
# Performance
"max_concurrency": 100,
# Advanced
"extra_kwargs": {
"top_p": 0.95,
"frequency_penalty": 0.0
}
}
)
Field Reference Table
| Field | Type | Required | Default | Description |
|---|
generators | Array | No | [] | List of generator configs |
teacher_prompt | String | Stim only | - | Teacher prompt name |
student_prompt | String | Stim only | - | Student prompt name |
model_name | String | Rollout only | - | Base model identifier |
max_tokens | Integer | No | - | Max tokens per generation |
temperature | Float | No | 1.0 | Generation temperature |
num_traj_per_stimulus | Integer | No | 1 | Trajectories per stimulus |
max_concurrency | Integer | No | 10 | Max concurrent requests |
extra_kwargs | Object | No | {} | Additional model params |
Template Inheritance
Targets can inherit from other targets:
# Base target
client.targets.set(
target_name="base_target",
repo_name="my_repo",
template="default",
overrides={
"model_name": "Qwen/Qwen3-32B",
"temperature": 1.0,
"max_tokens": 150
}
)
# Inherit and override
client.targets.set(
target_name="high_temp_target",
repo_name="my_repo",
template="base_target", # Inherit from base_target
overrides={
"temperature": 1.5 # Override only temperature
}
)
Next Steps
