Text Generation
Transformers
Safetensors
English
Hindi
Spanish
qwen3_5
image-text-to-text
router
planner
orchestration
tool-use
structured-output
json
lora
qwen3.5
health-assistant
conversational
Instructions to use meet4150/xevyo-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use meet4150/xevyo-01 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="meet4150/xevyo-01") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("meet4150/xevyo-01") model = AutoModelForMultimodalLM.from_pretrained("meet4150/xevyo-01", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use meet4150/xevyo-01 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "meet4150/xevyo-01" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "meet4150/xevyo-01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/meet4150/xevyo-01
- SGLang
How to use meet4150/xevyo-01 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "meet4150/xevyo-01" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "meet4150/xevyo-01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "meet4150/xevyo-01" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "meet4150/xevyo-01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use meet4150/xevyo-01 with Docker Model Runner:
docker model run hf.co/meet4150/xevyo-01
Download code/spec/example_input.schema.json from meet4150/xevyo-01: direct link, hf CLI and curl.
- Browser
- Download file 3.27 kB
-
https://huggingface.co/meet4150/xevyo-01/resolve/main/code/spec/example_input.schema.json
- Command line
-
hf download hf://meet4150/xevyo-01/code/spec/example_input.schema.json
-
curl -L -o example_input.schema.json https://huggingface.co/meet4150/xevyo-01/resolve/main/code/spec/example_input.schema.json
3.27 kB
| { | |
| "$schema": "https://json-schema.org/draft/2020-12/schema", | |
| "$id": "https://xevyo.local/spec/example_input.schema.json", | |
| "title": "xevyo-01 example input", | |
| "description": "What the calling application knows about one turn before the planner runs, and what every training/eval example stores next to its plan. The prompt renderer turns it into the chat messages the model reads. No user ids, no memory contents, no document text: the planner sees flags, not data.", | |
| "type": "object", | |
| "additionalProperties": false, | |
| "required": [ | |
| "message", | |
| "history", | |
| "attached_image", | |
| "remembered_image", | |
| "document_attached", | |
| "memory_enabled", | |
| "signed_in", | |
| "api_client", | |
| "offered_tools", | |
| "locale" | |
| ], | |
| "properties": { | |
| "message": { | |
| "description": "The user's latest message as typed. render clips it to its head and tail.", | |
| "type": "string", | |
| "minLength": 1, | |
| "maxLength": 100000 | |
| }, | |
| "history": { | |
| "description": "Earlier turns of this chat, oldest first, user and assistant only. render keeps the last 8 and clips each.", | |
| "type": "array", | |
| "maxItems": 200, | |
| "items": { | |
| "type": "object", | |
| "additionalProperties": false, | |
| "required": [ | |
| "role", | |
| "content" | |
| ], | |
| "properties": { | |
| "role": { | |
| "description": "Who said it.", | |
| "enum": [ | |
| "user", | |
| "assistant" | |
| ] | |
| }, | |
| "content": { | |
| "description": "What was said, as plain text (inline images already stripped).", | |
| "type": "string", | |
| "maxLength": 100000 | |
| } | |
| } | |
| } | |
| }, | |
| "attached_image": { | |
| "description": "THIS message carries an uploaded image.", | |
| "type": "boolean" | |
| }, | |
| "remembered_image": { | |
| "description": "The chat's remembered image: null for none, else the last generated image's prompt, or exactly 'the image you uploaded' when the remembered image is an earlier upload.", | |
| "type": [ | |
| "string", | |
| "null" | |
| ], | |
| "maxLength": 120 | |
| }, | |
| "document_attached": { | |
| "description": "A document is attached to this message or the chat has document context (attached_document_ids / build_document_context).", | |
| "type": "boolean" | |
| }, | |
| "memory_enabled": { | |
| "description": "The user's Memory switch is on (owui_settings.read_memory_switch). False also when the switch could not be read.", | |
| "type": "boolean" | |
| }, | |
| "signed_in": { | |
| "description": "An authenticated user (user_id != 'anonymous'). Memory commands and memory cards need it.", | |
| "type": "boolean" | |
| }, | |
| "api_client": { | |
| "description": "The chat came through a developer API key (request_intent.is_api_key_client): documents only on an explicit file request.", | |
| "type": "boolean" | |
| }, | |
| "offered_tools": { | |
| "description": "Tool names bound this turn (tools.json names), after user switches, health, calculator scope and Google connection. Only these may appear in plan.tools.", | |
| "type": "array", | |
| "uniqueItems": true, | |
| "maxItems": 40, | |
| "items": { | |
| "type": "string", | |
| "pattern": "^[a-z][a-z0-9_]{1,63}$" | |
| } | |
| }, | |
| "locale": { | |
| "description": "The client's locale (e.g. en-IN, hi-IN), or null when unknown. Context only.", | |
| "type": [ | |
| "string", | |
| "null" | |
| ], | |
| "maxLength": 20 | |
| } | |
| } | |
| } | |