You're looking at a specific version of this model. Jump to the model overview.
ltejedor /qwen3.8-27b-0.1:6406b350
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
|
Prompt to send to the model.
|
|
| system_prompt |
string
|
|
System prompt (chat models only). Leave empty for none.
|
| max_tokens |
integer
|
2048
Min: 1 |
Maximum number of tokens to generate.
|
| temperature |
number
|
0
Max: 2 |
Sampling temperature. 0 = greedy (deterministic).
|
| top_p |
number
|
1
Max: 1 |
Nucleus sampling probability mass. 1 disables it.
|
| top_k |
integer
|
-1
Min: -1 |
Top-k sampling. -1 disables it.
|
| min_p |
number
|
0
Max: 1 |
Minimum token probability relative to the most likely token. 0 disables it.
|
| repetition_penalty |
number
|
1.15
Min: 0.01 Max: 5 |
Penalize repeated tokens. 1 disables it; above 1 discourages repetition.
|
| presence_penalty |
number
|
0
Min: -2 Max: 2 |
Presence penalty.
|
| frequency_penalty |
number
|
0
Min: -2 Max: 2 |
Frequency penalty.
|
| enable_thinking |
boolean
|
False
|
Let the model reason before answering (models whose chat template supports thinking mode).
|
| stop |
string
|
|
Comma-separated stop sequences.
|
| seed |
integer
|
Random seed. Leave blank for random.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'type': 'string'},
'title': 'Output',
'type': 'array',
'x-cog-array-display': 'concatenate',
'x-cog-array-type': 'iterator'}