Instructions to use Feudor2/hallucination_detector_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Feudor2/hallucination_detector_v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Feudor2/hallucination_detector_v3") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Feudor2/hallucination_detector_v3") model = AutoModelForMultimodalLM.from_pretrained("Feudor2/hallucination_detector_v3") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Feudor2/hallucination_detector_v3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Feudor2/hallucination_detector_v3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Feudor2/hallucination_detector_v3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Feudor2/hallucination_detector_v3
- SGLang
How to use Feudor2/hallucination_detector_v3 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 "Feudor2/hallucination_detector_v3" \ --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": "Feudor2/hallucination_detector_v3", "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 "Feudor2/hallucination_detector_v3" \ --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": "Feudor2/hallucination_detector_v3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Feudor2/hallucination_detector_v3 with Docker Model Runner:
docker model run hf.co/Feudor2/hallucination_detector_v3
| <s>{%- set names = {'assistant': ' Ассистент:', 'user': ' Пользователь:'} %} | |
| {%- set tools_prefix = 'Тебе доступны следующие функции:' %} | |
| {%- macro __render_tool(tool) %} | |
| {%- set name = tool.function.name %} | |
| {%- set description = tool.function.description|default('') %} | |
| {%- set parameters = tool.function.parameters|tojson %} | |
| {{- '\n' }}function {{ '{' }}'name':'{{ name }}', | |
| {%- if tool.description %}'description':'{{ description }}',{% endif %} | |
| 'parameters':{{ parameters }} | |
| {{- '}' }} | |
| {%- endmacro %} | |
| {%- macro __render_tools(tools) %} | |
| {{- tools_prefix }} | |
| {%- for tool in tools %} | |
| {{- __render_tool(tool) }} | |
| {%- endfor %} | |
| {{- '\n\n' }} | |
| {%- endmacro %} | |
| {%- macro __render_tool_message(message) %} | |
| {{- '\n\nРезультат вызова' }} {{ message.name }}: {{ message.content }} {{ '\n\n' }} | |
| {%- endmacro %} | |
| {%- if tools -%} | |
| {{- __render_tools(tools) }} | |
| {%- endif -%} | |
| {%- macro __render_user_message(message) %} | |
| {{ names.user }} {{ message.content + '\n\n' }} | |
| {%- endmacro %} | |
| {%- macro __render_assistant_message(message) %} | |
| {{- names.assistant }} | |
| {%- set call = message['function_call'] %} | |
| {%- if call %} | |
| {{- '\n[TOOL_CALL_START]' }}{{ call.name }}{{ '\n' }}{{ call.arguments|tojson }} | |
| {%- else %} | |
| {{- ' ' + message.content + '\n\n' }} | |
| {%- endif %} | |
| {%- endmacro %} | |
| {%- if not add_generation_prompt is defined %} | |
| {%- set add_generation_prompt = false %} | |
| {%- endif %} | |
| {%- for message in messages %} | |
| {%- if message['role'] == 'user' %} | |
| {{- __render_user_message(message) }} | |
| {%- endif %} | |
| {%- if message.role == 'assistant' and not loop.last %} | |
| {{- __render_assistant_message(message) }} | |
| {%- endif %} | |
| {%- if message.role == 'tool' %} | |
| {{- __render_tool_message(message) }} | |
| {%- endif %} | |
| {%- if loop.last %} | |
| {{- ' Ассистент:[SEP]' }} | |
| {%- endif %} | |
| {%- endfor %} | |