Instructions to use calmresearch-ai/Model3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use calmresearch-ai/Model3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="calmresearch-ai/Model3")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("calmresearch-ai/Model3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use calmresearch-ai/Model3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "calmresearch-ai/Model3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "calmresearch-ai/Model3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/calmresearch-ai/Model3
- SGLang
How to use calmresearch-ai/Model3 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 "calmresearch-ai/Model3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "calmresearch-ai/Model3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "calmresearch-ai/Model3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "calmresearch-ai/Model3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use calmresearch-ai/Model3 with Docker Model Runner:
docker model run hf.co/calmresearch-ai/Model3
Download encoding/tests/test_input_4.json from calmresearch-ai/Model3: direct link, hf CLI and curl.
- Browser
- Download file 712 Bytes
-
https://huggingface.co/calmresearch-ai/Model3/resolve/main/encoding/tests/test_input_4.json
- Command line
-
hf download hf://calmresearch-ai/Model3/encoding/tests/test_input_4.json
-
curl -L -o test_input_4.json https://huggingface.co/calmresearch-ai/Model3/resolve/main/encoding/tests/test_input_4.json
712 Bytes
| [ | |
| { | |
| "role": "system", | |
| "content": "该助手为DeepSeek-V3,由深度求索公司创造。\n今天是2025年10月17日,星期五。" | |
| }, | |
| { | |
| "role": "latest_reminder", | |
| "content": "2024-11-15,上海市,App,中文" | |
| }, | |
| { | |
| "role": "user", | |
| "content": "热海大滚锅是世界著名温泉吗" | |
| }, | |
| { | |
| "role": "assistant", | |
| "content": "热海大滚锅在中国乃至全球的地热奇观中占有重要地位,但“世界著名”的称号更侧重于它作为独特的地质现象和旅游景点。", | |
| "mask": 1 | |
| }, | |
| { | |
| "role": "user", | |
| "content": "世界著名温泉有哪些", | |
| "task": "action" | |
| }, | |
| { | |
| "role": "assistant", | |
| "content": "Search" | |
| } | |
| ] | |