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/turn_plan.schema.json from meet4150/xevyo-01: direct link, hf CLI and curl.
- Browser
- Download file 8.73 kB
-
https://huggingface.co/meet4150/xevyo-01/resolve/main/code/spec/turn_plan.schema.json
- Command line
-
hf download hf://meet4150/xevyo-01/code/spec/turn_plan.schema.json
-
curl -L -o turn_plan.schema.json https://huggingface.co/meet4150/xevyo-01/resolve/main/code/spec/turn_plan.schema.json
8.73 kB
| { | |
| "$schema": "https://json-schema.org/draft/2020-12/schema", | |
| "$id": "https://xevyo.local/spec/turn_plan.schema.json", | |
| "title": "xevyo-01 turn plan", | |
| "description": "One plan per chat turn. Canonical form lists keys in this order and OMITS every field that holds its default, so a typical plan is short. Decision fields describe what the message needs whatever tools are offered; only `tools` depends on the offered set. Conditional rules (e.g. doc_format only with a document, edit only with an image to edit) are checked after decoding, not here, so this file stays usable for guided decoding.", | |
| "type": "object", | |
| "additionalProperties": false, | |
| "required": [ | |
| "schema_version" | |
| ], | |
| "properties": { | |
| "schema_version": { | |
| "description": "Plan format version. Always xv01.1.", | |
| "const": "xv01.1" | |
| }, | |
| "safety_concern": { | |
| "description": "A concern the planner raises. Code takes the higher of this and its own safety screen and never lowers its own. Rank: none < medication_risk < possible_emergency < possible_crisis. Default none.", | |
| "enum": [ | |
| "none", | |
| "medication_risk", | |
| "possible_emergency", | |
| "possible_crisis" | |
| ], | |
| "default": "none" | |
| }, | |
| "image": { | |
| "description": "What to do with images this turn. Omitted = action none.", | |
| "type": "object", | |
| "additionalProperties": false, | |
| "required": [ | |
| "action" | |
| ], | |
| "properties": { | |
| "action": { | |
| "description": "generate a new picture, edit the attached or remembered one, analyze the attached one, or none.", | |
| "enum": [ | |
| "none", | |
| "generate", | |
| "edit", | |
| "analyze" | |
| ] | |
| }, | |
| "prompt": { | |
| "description": "generate only: the visual scene in English, 10-40 words, no words meant to appear as text.", | |
| "type": "string", | |
| "minLength": 1, | |
| "maxLength": 400 | |
| }, | |
| "visible_text": { | |
| "description": "generate only: the exact words to show, one short line, only words the user gave; empty string for no text.", | |
| "type": "string", | |
| "maxLength": 200 | |
| }, | |
| "instruction": { | |
| "description": "edit only: the change as a short English command.", | |
| "type": "string", | |
| "minLength": 1, | |
| "maxLength": 300 | |
| } | |
| } | |
| }, | |
| "request_kind": { | |
| "description": "chat = answer in the reply; document = make a file with doc-gen. Default chat.", | |
| "enum": [ | |
| "chat", | |
| "document" | |
| ], | |
| "default": "chat" | |
| }, | |
| "doc_format": { | |
| "description": "Only with request_kind document: pptx decks, xlsx spreadsheets/data tables, docx when Word is named, pdf otherwise.", | |
| "enum": [ | |
| "pdf", | |
| "docx", | |
| "xlsx", | |
| "pptx", | |
| null | |
| ], | |
| "default": null | |
| }, | |
| "clarify": { | |
| "description": "A question to ask back instead of answering. Omitted = none.", | |
| "type": [ | |
| "string", | |
| "null" | |
| ], | |
| "minLength": 3, | |
| "maxLength": 300, | |
| "default": null | |
| }, | |
| "standalone_question": { | |
| "description": "The message restated so it needs no history, or the question left after a memory command. Omitted when the message already stands alone.", | |
| "type": [ | |
| "string", | |
| "null" | |
| ], | |
| "minLength": 1, | |
| "maxLength": 400, | |
| "default": null | |
| }, | |
| "needs_search": { | |
| "description": "Answering correctly needs live web data. Default false.", | |
| "type": "boolean", | |
| "default": false | |
| }, | |
| "search_queries": { | |
| "description": "With needs_search only: 1-3 standalone search phrases, the question itself first. Keep 'near me' as typed; code adds the saved place.", | |
| "type": "array", | |
| "minItems": 1, | |
| "maxItems": 3, | |
| "items": { | |
| "type": "string", | |
| "minLength": 3, | |
| "maxLength": 300 | |
| } | |
| }, | |
| "data_tool": { | |
| "description": "A calculator or food-database question. Default none.", | |
| "enum": [ | |
| "none", | |
| "calc", | |
| "bmi", | |
| "dose", | |
| "barcode", | |
| "usda", | |
| "food" | |
| ], | |
| "default": "none" | |
| }, | |
| "drug": { | |
| "description": "A medication question and the medicines it names. Omitted = not a medication question.", | |
| "type": [ | |
| "object", | |
| "null" | |
| ], | |
| "additionalProperties": false, | |
| "required": [ | |
| "names" | |
| ], | |
| "properties": { | |
| "names": { | |
| "description": "Medicine names as the user wrote them, lowercased, known or not; not vitamins or supplements.", | |
| "type": "array", | |
| "minItems": 1, | |
| "maxItems": 3, | |
| "items": { | |
| "type": "string", | |
| "minLength": 2, | |
| "maxLength": 60 | |
| } | |
| }, | |
| "wants_research": { | |
| "description": "The user also asked for studies or evidence. Default false.", | |
| "type": "boolean", | |
| "default": false | |
| } | |
| }, | |
| "default": null | |
| }, | |
| "memory": { | |
| "description": "An explicit memory request. Omitted = action none.", | |
| "type": "object", | |
| "additionalProperties": false, | |
| "required": [ | |
| "action" | |
| ], | |
| "properties": { | |
| "action": { | |
| "description": "remember a fact, forget one (or everything), recall what is stored, or none.", | |
| "enum": [ | |
| "none", | |
| "remember", | |
| "forget", | |
| "recall" | |
| ] | |
| }, | |
| "memory_type": { | |
| "description": "remember only: the category of the fact (order: allergy > medication > medical_condition > preference > fact; location for a move; vital for a body measurement).", | |
| "enum": [ | |
| "allergy", | |
| "medication", | |
| "medical_condition", | |
| "preference", | |
| "fact", | |
| "location", | |
| "vital" | |
| ] | |
| }, | |
| "content": { | |
| "description": "remember: the fact in profile style ('Is vegetarian' -> 'Vegetarian', 'Takes metformin'); forget: what to forget, '*' for everything.", | |
| "type": "string", | |
| "minLength": 1, | |
| "maxLength": 300 | |
| } | |
| } | |
| }, | |
| "domain": { | |
| "description": "What kind of turn this is. Default general.", | |
| "enum": [ | |
| "general", | |
| "medical", | |
| "coding", | |
| "personal_memory", | |
| "prompt_authoring" | |
| ], | |
| "default": "general" | |
| }, | |
| "depth": { | |
| "description": "How much work the answer needs. With needs_tools it maps losslessly to tier/strategy: quick=T1, normal=T2 or T3, deep=T4, research=T5. Default normal.", | |
| "enum": [ | |
| "quick", | |
| "normal", | |
| "deep", | |
| "research" | |
| ], | |
| "default": "normal" | |
| }, | |
| "needs_tools": { | |
| "description": "The turn needs the agent path (tools, memory rules, medical rules), not the tool-less fast path. Default false.", | |
| "type": "boolean", | |
| "default": false | |
| }, | |
| "tools": { | |
| "description": "Ordered tool calls code should run for this turn, chosen ONLY from the offered tools. Web search, drug_lookup, generate_image and memory writes are never listed: needs_search, drug, image and memory drive them. Default empty.", | |
| "type": "array", | |
| "maxItems": 4, | |
| "items": { | |
| "type": "object", | |
| "additionalProperties": false, | |
| "required": [ | |
| "name", | |
| "arguments" | |
| ], | |
| "properties": { | |
| "name": { | |
| "description": "A tool name from tools.json that was offered this turn.", | |
| "enum": [ | |
| "fetch_page", | |
| "kb_retrieve", | |
| "code_agent", | |
| "check_drug_interactions", | |
| "calculate_bmi", | |
| "calculate_dosage", | |
| "calculate", | |
| "open_food_facts", | |
| "usda_food_search", | |
| "open_fda", | |
| "dsld_lookup", | |
| "pharmgkb_lookup", | |
| "google_trends_search", | |
| "semantic_scholar_search", | |
| "openaq_air_quality", | |
| "google_calendar_list_events", | |
| "google_calendar_create_event", | |
| "google_calendar_delete_event", | |
| "google_calendar_list_calendars", | |
| "google_health_read", | |
| "google_health_list_data_sources", | |
| "handoff_to" | |
| ] | |
| }, | |
| "arguments": { | |
| "description": "Arguments by parameter name; validated per tool against tools.json. A string argument may be exactly $MESSAGE to mean the user's message as typed.", | |
| "type": "object", | |
| "additionalProperties": { | |
| "type": [ | |
| "string", | |
| "number", | |
| "integer", | |
| "boolean" | |
| ] | |
| } | |
| } | |
| } | |
| }, | |
| "default": [] | |
| }, | |
| "directives": { | |
| "description": "Per-turn prompt directives by id, from the planner-selectable part of directives.json, in catalogue order. Default empty.", | |
| "type": "array", | |
| "uniqueItems": true, | |
| "maxItems": 6, | |
| "items": { | |
| "enum": [ | |
| "safety.medication", | |
| "safety.undiagnosed_pain", | |
| "context.unseen_reference", | |
| "memory.self_fact", | |
| "style.statement_only", | |
| "style.casual", | |
| "style.followup", | |
| "lang.hinglish", | |
| "lang.hinglish_english", | |
| "lang.devanagari" | |
| ] | |
| }, | |
| "default": [] | |
| } | |
| } | |
| } | |