Text Generation
Transformers
Safetensors
qwen3
RAG
function-calling
structured-generation
enterprise
italian
conversational
text-generation-inference
Instructions to use and-emili/aera-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use and-emili/aera-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="and-emili/aera-4b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("and-emili/aera-4b") model = AutoModelForMultimodalLM.from_pretrained("and-emili/aera-4b") 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use and-emili/aera-4b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "and-emili/aera-4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "and-emili/aera-4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/and-emili/aera-4b
- SGLang
How to use and-emili/aera-4b 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 "and-emili/aera-4b" \ --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": "and-emili/aera-4b", "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 "and-emili/aera-4b" \ --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": "and-emili/aera-4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use and-emili/aera-4b with Docker Model Runner:
docker model run hf.co/and-emili/aera-4b
| { | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "151643": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151644": { | |
| "content": "<|im_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151645": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151646": { | |
| "content": "<|object_ref_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151647": { | |
| "content": "<|object_ref_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151648": { | |
| "content": "<|box_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151649": { | |
| "content": "<|box_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151650": { | |
| "content": "<|quad_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151651": { | |
| "content": "<|quad_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151652": { | |
| "content": "<|vision_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151653": { | |
| "content": "<|vision_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151654": { | |
| "content": "<|vision_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151655": { | |
| "content": "<|image_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151656": { | |
| "content": "<|video_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151657": { | |
| "content": "<tool_call>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151658": { | |
| "content": "</tool_call>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151659": { | |
| "content": "<|fim_prefix|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151660": { | |
| "content": "<|fim_middle|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151661": { | |
| "content": "<|fim_suffix|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151662": { | |
| "content": "<|fim_pad|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151663": { | |
| "content": "<|repo_name|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151664": { | |
| "content": "<|file_sep|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151665": { | |
| "content": "<tool_response>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151666": { | |
| "content": "</tool_response>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151667": { | |
| "content": "<think>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "151668": { | |
| "content": "</think>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|object_ref_start|>", | |
| "<|object_ref_end|>", | |
| "<|box_start|>", | |
| "<|box_end|>", | |
| "<|quad_start|>", | |
| "<|quad_end|>", | |
| "<|vision_start|>", | |
| "<|vision_end|>", | |
| "<|vision_pad|>", | |
| "<|image_pad|>", | |
| "<|video_pad|>" | |
| ], | |
| "bos_token": null, | |
| "chat_template": "{%- set first_message = messages[0] if messages else none -%}\n{%- set system_message = first_message.content if first_message and first_message.role == 'system' else none -%}\n{%- set message_start = 1 if system_message else 0 -%}\n{%- if system_message or (tools and tools|length > 0) -%}\n{{- '<|im_start|>system\n' }}\n{%- if system_message -%}\n{{- system_message }}\n{%- endif -%}\n{%- if system_message and tools and tools|length > 0 -%}\n{{- '\n\nAvailable tools:' }}\n{%- elif tools and tools|length > 0 -%}\n{{- 'Available tools:' }}\n{%- endif -%}\n{%- if tools -%}\n{%- for tool in tools %}\n{{- '\n<tool>\n' }}\n{{- 'name: ' + tool['function']['name'] + '\n' }}\n{{- 'description: ' + tool['function']['description'] + '\n' }}\n{{- 'parameters:\n' }}\n{%- for param_name, param_info in tool['function']['parameters']['properties'].items() %}\n{{- ' ' + param_name + ': ' + param_info.get('description', '') + '\n' }}\n{%- endfor %}\n{%- if tool['function']['parameters'].get('required') %}\n{{- 'required: ' + tool['function']['parameters']['required']|tojson + '\n' }}\n{%- endif %}\n{{- '</tool>' }}\n{%- endfor %}\n{{- '\n' }}\n{%- endif -%}\n{{- '<|im_end|>\n' }}\n{%- endif %}\n{%- for i in range(message_start, messages|length) %}\n {%- set message = messages[i] %}\n {%- if message['role'] == 'user' %}\n {{- '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' }}\n {%- elif message['role'] == 'assistant' and message.get('tool_calls') %}\n {{- '<|im_start|>assistant\n' }}\n {%- if message.get('content') %}\n {{- message['content'] + '\n' }}\n {%- endif %}\n {%- for tool_call in message['tool_calls'] %}\n {{- '<tool_call>\n' }}\n {{- 'id: ' + tool_call['id'] + '\n' }}\n {{- 'name: ' + tool_call['function']['name'] + '\n' }}\n {{- 'arguments: ' + tool_call['function']['arguments'] | tojson + '\n' }}\n {{- '</tool_call>\n' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message['role'] == 'assistant' %}\n {{- '<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}\n {%- elif message['role'] == 'tool' %}\n {{- '<|im_start|>tool\n' }}\n {{- 'tool_call_id: ' + message.get('tool_call_id', '') + '\n' }}\n {{- 'content: ' + message['content'] + '\n' }}\n {{- '<|im_end|>\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "extra_special_tokens": {}, | |
| "model_max_length": 40960, | |
| "pad_token": "<|vision_pad|>", | |
| "padding_side": "left", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null | |
| } | |