Text Generation
Transformers
Safetensors
English
Chinese
PanguEmbedded
medical
reasoning
conversational
custom_code
Instructions to use FreedomIntelligence/HuatuoGPT-3-7B-Pangu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FreedomIntelligence/HuatuoGPT-3-7B-Pangu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FreedomIntelligence/HuatuoGPT-3-7B-Pangu", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT-3-7B-Pangu", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use FreedomIntelligence/HuatuoGPT-3-7B-Pangu with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FreedomIntelligence/HuatuoGPT-3-7B-Pangu" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FreedomIntelligence/HuatuoGPT-3-7B-Pangu", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FreedomIntelligence/HuatuoGPT-3-7B-Pangu
- SGLang
How to use FreedomIntelligence/HuatuoGPT-3-7B-Pangu 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 "FreedomIntelligence/HuatuoGPT-3-7B-Pangu" \ --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": "FreedomIntelligence/HuatuoGPT-3-7B-Pangu", "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 "FreedomIntelligence/HuatuoGPT-3-7B-Pangu" \ --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": "FreedomIntelligence/HuatuoGPT-3-7B-Pangu", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FreedomIntelligence/HuatuoGPT-3-7B-Pangu with Docker Model Runner:
docker model run hf.co/FreedomIntelligence/HuatuoGPT-3-7B-Pangu
| {"add_bos_token": true, "add_eos_token": false, "add_prefix_space": true, "added_tokens_decoder": {"0": {"content": "<unk>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "</s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45806": {"content": "<|User|>:", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45813": {"content": "<|Bot|>:", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45830": {"content": "[unused0]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45840": {"content": "[unused1]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45846": {"content": "[unused2]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45849": {"content": "[unused3]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45861": {"content": "[unused4]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45866": {"content": "[unused5]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45874": {"content": "[unused6]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45883": {"content": "[unused7]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45884": {"content": "[unused8]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45887": {"content": "[unused9]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45892": {"content": "[unused10]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45920": {"content": "[unused11]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45932": {"content": "[unused12]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45938": {"content": "[unused13]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45953": {"content": "[unused14]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45968": {"content": "[unused15]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45974": {"content": "[unused16]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45982": {"content": "[unused17]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "45986": {"content": "[unused18]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46005": {"content": "[unused19]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46007": {"content": "[unused20]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46014": {"content": "[unused21]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46017": {"content": "[unused22]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46028": {"content": "[unused23]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46032": {"content": "[unused24]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46081": {"content": "[unused25]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46086": {"content": "[unused26]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46101": {"content": "[unused27]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46183": {"content": "[unused28]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46230": {"content": "[unused29]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46245": {"content": "[unused30]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "46257": {"content": "[unused31]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "144208": {"content": "[unused32]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "144209": {"content": "[unused33]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "auto_map": {"AutoTokenizer": ["tokenization_openpangu.PanguTokenizer", null]}, "bos_token": "<s>", "clean_up_tokenization_spaces": false, "eos_token": "[unused10]", "legacy": true, "model_max_length": 1000000000000000019884624838656, "pad_token": "<unk>", "sp_model_kwargs": {}, "spaces_between_special_tokens": false, "tokenizer_class": "PanguTokenizer", "unk_token": "<unk>", "use_default_system_prompt": false, "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '[unused9]系统:[unused10]' }}{% endif %}{% if message['role'] == 'system' %}{{ '[unused9]系统:' + message['content'] + '[unused10]' }}{% endif %}{% if message['role'] == 'assistant' %}{{'[unused9]助手:' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'tool' %}{{'[unused9]工具:' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'function' %}{{'[unused9]方法:' + message['content'] + '[unused10]'}}{% endif %}{% if message['role'] == 'user' %}{{'[unused9]用户:' + message['content'] + '[unused10]'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[unused9]助手:' }}{% endif %}"} | |