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/directives.json from meet4150/xevyo-01: direct link, hf CLI and curl.
- Browser
- Download file 9.02 kB
-
https://huggingface.co/meet4150/xevyo-01/resolve/main/code/spec/directives.json
- Command line
-
hf download hf://meet4150/xevyo-01/code/spec/directives.json
-
curl -L -o directives.json https://huggingface.co/meet4150/xevyo-01/resolve/main/code/spec/directives.json
9.02 kB
| { | |
| "catalogue_version": "xv01.1", | |
| "directives": [ | |
| { | |
| "id": "safety.medication", | |
| "kind": "planner", | |
| "meaning": "A question about a medicine or a pregnancy: do not call anything safe; state the risk, refer to a pharmacist or doctor; no child dose or own-dose change except a calculator result.", | |
| "combine": "union", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": {}, | |
| "excluded_domains": [ | |
| "coding", | |
| "personal_memory", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "safety.undiagnosed_pain", | |
| "kind": "planner", | |
| "meaning": "Abdominal pain that has lasted days with no diagnosis: suggest no medicine or home remedy; say what makes it urgent and that a doctor should examine it.", | |
| "combine": "union", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": {}, | |
| "excluded_domains": [ | |
| "coding", | |
| "personal_memory", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "context.unseen_reference", | |
| "kind": "planner", | |
| "meaning": "A first message points at material the conversation does not contain ('the study', 'the 0.2% figure'): answer the likeliest reading and say so, or ask one short question.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": { | |
| "history_empty": true, | |
| "document_attached": false | |
| }, | |
| "excluded_domains": [], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "memory.self_fact", | |
| "kind": "planner", | |
| "meaning": "The user states a lasting fact about themselves (home, work, family, diet, routine, health): run the memory agent now and offer the Save card; never claim it is saved.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": { | |
| "signed_in": true, | |
| "memory_enabled": true | |
| }, | |
| "excluded_domains": [], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "style.statement_only", | |
| "kind": "planner", | |
| "meaning": "The user only states standing facts about themselves, asking nothing: reply in one or two sentences acknowledging each; no search, advice, referral or question.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": {}, | |
| "excluded_domains": [ | |
| "coding", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "style.casual", | |
| "kind": "planner", | |
| "meaning": "A short one-line casual question that wants a short answer: a few plain sentences, no list, bold or headings; at most three likely causes for a symptom.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": { | |
| "document_attached": false | |
| }, | |
| "excluded_domains": [ | |
| "coding", | |
| "personal_memory", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ], | |
| "excluded_safety": [ | |
| "possible_emergency", | |
| "possible_crisis" | |
| ] | |
| }, | |
| { | |
| "id": "style.followup", | |
| "kind": "planner", | |
| "meaning": "A one-line follow-up (14 words or fewer) asking for no particular shape: when it is answered from search results, reply in a few plain sentences with no headings or bold.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "agent" | |
| ], | |
| "requires": { | |
| "history_empty": false | |
| }, | |
| "excluded_domains": [ | |
| "coding", | |
| "personal_memory", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ], | |
| "excluded_safety": [ | |
| "possible_emergency", | |
| "possible_crisis" | |
| ] | |
| }, | |
| { | |
| "id": "lang.hinglish", | |
| "kind": "planner", | |
| "meaning": "Small talk written in Hindi with Roman letters: reply the same way (Roman Hindi, no Devanagari, not English).", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "fast", | |
| "agent" | |
| ], | |
| "requires": {}, | |
| "excluded_domains": [ | |
| "coding", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "lang.hinglish_english", | |
| "kind": "planner", | |
| "meaning": "Anything other than small talk written in Hindi with Roman letters (health above all): reply in plain simple English, naming symptoms and body parts in English.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "fast", | |
| "agent" | |
| ], | |
| "requires": {}, | |
| "excluded_domains": [ | |
| "coding", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "lang.devanagari", | |
| "kind": "planner", | |
| "meaning": "The message is Hindi written in Devanagari: reply in Hindi in Devanagari.", | |
| "combine": "planner_gated", | |
| "paths": [ | |
| "fast", | |
| "agent" | |
| ], | |
| "requires": {}, | |
| "excluded_domains": [ | |
| "coding", | |
| "prompt_authoring" | |
| ], | |
| "excluded_image_actions": [ | |
| "generate", | |
| "edit" | |
| ] | |
| }, | |
| { | |
| "id": "frame.realtime_results", | |
| "kind": "derived", | |
| "meaning": "[REALTIME/FACTUAL QUERY] answer only from the live results below; do not search again." | |
| }, | |
| { | |
| "id": "frame.realtime_reference_only", | |
| "kind": "derived", | |
| "meaning": "[FACTUAL QUERY] use the reference material where it answers; say what could not be confirmed." | |
| }, | |
| { | |
| "id": "frame.realtime_nothing_found", | |
| "kind": "derived", | |
| "meaning": "[FACTUAL QUERY] answer from own knowledge, say briefly what could not be confirmed." | |
| }, | |
| { | |
| "id": "frame.realtime_must_search", | |
| "kind": "derived", | |
| "meaning": "[REALTIME/FACTUAL QUERY] you MUST call web_search or web_rag; post-run backstop applies." | |
| }, | |
| { | |
| "id": "frame.personal_query", | |
| "kind": "derived", | |
| "meaning": "[PERSONAL QUERY] answer from memory, do not web search." | |
| }, | |
| { | |
| "id": "frame.followup_restated", | |
| "kind": "derived", | |
| "meaning": "[FOLLOW-UP] the latest message asks: <standalone_question>. Answer that question." | |
| }, | |
| { | |
| "id": "frame.document_task", | |
| "kind": "derived", | |
| "meaning": "[DOCUMENT TASK] / [UPLOADED FILE(S)] answer from the uploaded documents when the question is about them." | |
| }, | |
| { | |
| "id": "note.grounding", | |
| "kind": "derived", | |
| "meaning": "[GROUNDING NOTE] state only what the record holds; never fill in typical values." | |
| }, | |
| { | |
| "id": "frame.medication_label", | |
| "kind": "derived", | |
| "meaning": "[MEDICATION QUESTION] answer from the official label below; no papers unless wants_research." | |
| }, | |
| { | |
| "id": "frame.medication_lookup", | |
| "kind": "derived", | |
| "meaning": "[MEDICATION QUESTION] call drug_lookup first; never present papers as drug information." | |
| }, | |
| { | |
| "id": "data.calc", | |
| "kind": "derived", | |
| "meaning": "[CALCULATION] use the calculate tool; one expression including rounding; temperature pinned to 0.1." | |
| }, | |
| { | |
| "id": "data.bmi", | |
| "kind": "derived", | |
| "meaning": "[BMI CALCULATION] call calculate_bmi in the user's units; report exactly." | |
| }, | |
| { | |
| "id": "data.dose", | |
| "kind": "derived", | |
| "meaning": "[DOSE CALCULATION] call calculate_dosage; a mg/kg figure drops the drug label prefetch." | |
| }, | |
| { | |
| "id": "data.barcode", | |
| "kind": "derived", | |
| "meaning": "[PRODUCT LOOKUP] open_food_facts by barcode; no web search." | |
| }, | |
| { | |
| "id": "data.nutrition", | |
| "kind": "derived", | |
| "meaning": "[NUTRITION LOOKUP] usda_food_search with the food as specific as the user said." | |
| }, | |
| { | |
| "id": "memory.server_handled", | |
| "kind": "derived", | |
| "meaning": "[MEMORY COMMAND HANDLED BY THE SERVER] do not call memory tools or claim a save; answer the rest." | |
| }, | |
| { | |
| "id": "memory.server_verified", | |
| "kind": "derived", | |
| "meaning": "[SERVER-VERIFIED MEMORY ACTION] saved / NOT saved (consent) / pending confirmation." | |
| }, | |
| { | |
| "id": "note.health_memory_off", | |
| "kind": "derived", | |
| "meaning": "[HEALTH MEMORY OFF] say how to turn it on, not that records are inaccessible." | |
| }, | |
| { | |
| "id": "note.premise_hipaa", | |
| "kind": "derived", | |
| "meaning": "VERIFIED FACT FOR THIS TURN: the cited 45 CFR section does not exist." | |
| }, | |
| { | |
| "id": "note.pasted_injection", | |
| "kind": "derived", | |
| "meaning": "The pasted text is framed as untrusted data; the user's own request stays outside the frame." | |
| }, | |
| { | |
| "id": "note.history_cut", | |
| "kind": "derived", | |
| "meaning": "Only the recent part of the conversation is visible; say so instead of guessing." | |
| }, | |
| { | |
| "id": "note.regenerated_not_edited", | |
| "kind": "derived", | |
| "meaning": "Tell the user the image was re-generated, not edited." | |
| }, | |
| { | |
| "id": "guard.no_image_this_turn", | |
| "kind": "derived", | |
| "meaning": "The agent's own generate_image is refused this turn (RepeatedImageGuard)." | |
| }, | |
| { | |
| "id": "note.live_figure", | |
| "kind": "derived", | |
| "meaning": "LIVE_DATA_NOTE / MOVING_FIGURE_NOTE on the results block." | |
| } | |
| ] | |
| } | |