ltejedor/qwen3.8-27b-0.1

Qwen3.8 27B served with vLLM

Public

97 runs

Weights

Run ltejedor/qwen3.8-27b-0.1 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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.

{
  "type": "object",
  "title": "Input",
  "required": [
    "prompt"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 12,
      "nullable": true,
      "description": "Random seed. Leave blank for random."
    },
    "stop": {
      "type": "string",
      "title": "Stop",
      "default": "",
      "x-order": 11,
      "description": "Comma-separated stop sequences."
    },
    "min_p": {
      "type": "number",
      "title": "Min P",
      "default": 0,
      "maximum": 1,
      "minimum": 0,
      "x-order": 6,
      "description": "Minimum token probability relative to the most likely token. 0 disables it."
    },
    "top_k": {
      "type": "integer",
      "title": "Top K",
      "default": -1,
      "minimum": -1,
      "x-order": 5,
      "description": "Top-k sampling. -1 disables it."
    },
    "top_p": {
      "type": "number",
      "title": "Top P",
      "default": 1,
      "maximum": 1,
      "minimum": 0,
      "x-order": 4,
      "description": "Nucleus sampling probability mass. 1 disables it."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 0,
      "description": "Prompt to send to the model."
    },
    "max_tokens": {
      "type": "integer",
      "title": "Max Tokens",
      "default": 2048,
      "minimum": 1,
      "x-order": 2,
      "description": "Maximum number of tokens to generate."
    },
    "temperature": {
      "type": "number",
      "title": "Temperature",
      "default": 0,
      "maximum": 2,
      "minimum": 0,
      "x-order": 3,
      "description": "Sampling temperature. 0 = greedy (deterministic)."
    },
    "system_prompt": {
      "type": "string",
      "title": "System Prompt",
      "default": "",
      "x-order": 1,
      "description": "System prompt (chat models only). Leave empty for none."
    },
    "enable_thinking": {
      "type": "boolean",
      "title": "Enable Thinking",
      "default": false,
      "x-order": 10,
      "description": "Let the model reason before answering (models whose chat template supports thinking mode)."
    },
    "presence_penalty": {
      "type": "number",
      "title": "Presence Penalty",
      "default": 0,
      "maximum": 2,
      "minimum": -2,
      "x-order": 8,
      "description": "Presence penalty."
    },
    "frequency_penalty": {
      "type": "number",
      "title": "Frequency Penalty",
      "default": 0,
      "maximum": 2,
      "minimum": -2,
      "x-order": 9,
      "description": "Frequency penalty."
    },
    "repetition_penalty": {
      "type": "number",
      "title": "Repetition Penalty",
      "default": 1.15,
      "maximum": 5,
      "minimum": 0.01,
      "x-order": 7,
      "description": "Penalize repeated tokens. 1 disables it; above 1 discourages repetition."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "array",
  "items": {
    "type": "string"
  },
  "title": "Output",
  "x-cog-array-type": "iterator",
  "x-cog-array-display": "concatenate"
}