You're looking at a specific version of this model. Jump to the model overview.
spuuntries /llada-8b-kcv:d6af149e
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
Field | Type | Default value | Description |
---|---|---|---|
prompt |
string
|
Input text for generation
|
|
system_prompt |
string
|
Asisten adalah chatbot bernama Anita, seorang chatbot yang ramah.
|
System prompt to guide model behavior
|
prompt_template |
string
|
<|startoftext|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
Template for formatting prompts
|
max_tokens |
integer
|
256
Min: 1 |
Maximum length of generated text
|
temperature |
number
|
0.5
Max: 1 |
Sampling temperature (higher = more random)
|
steps |
integer
|
32
Min: 1 |
Number of denoising steps per block
|
block_length |
integer
|
32
Min: 1 |
Length of parallel generation blocks
|
cfg_scale |
number
|
0
|
Classifier-free guidance scale
|
seed |
integer
|
Random seed for reproducible generation
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'description': 'Output class for the LLaDA predictor, containing generated '
'text states',
'properties': {'final_output': {'title': 'Final Output', 'type': 'string'},
'states': {'items': {'type': 'string'},
'title': 'States',
'type': 'array'}},
'required': ['states', 'final_output'],
'title': 'Output',
'type': 'object'}