Text Generation
Transformers
Safetensors
English
Chinese
llama
llm
nanbeige
conversational
text-generation-inference
Instructions to use Nanbeige/Nanbeige4.3-33B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nanbeige/Nanbeige4.3-33B-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Nanbeige/Nanbeige4.3-33B-Base") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Nanbeige/Nanbeige4.3-33B-Base") model = AutoModelForCausalLM.from_pretrained("Nanbeige/Nanbeige4.3-33B-Base", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Nanbeige/Nanbeige4.3-33B-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Nanbeige/Nanbeige4.3-33B-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Nanbeige/Nanbeige4.3-33B-Base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Nanbeige/Nanbeige4.3-33B-Base
- SGLang
How to use Nanbeige/Nanbeige4.3-33B-Base 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 "Nanbeige/Nanbeige4.3-33B-Base" \ --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": "Nanbeige/Nanbeige4.3-33B-Base", "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 "Nanbeige/Nanbeige4.3-33B-Base" \ --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": "Nanbeige/Nanbeige4.3-33B-Base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Nanbeige/Nanbeige4.3-33B-Base with Docker Model Runner:
docker model run hf.co/Nanbeige/Nanbeige4.3-33B-Base
Download tokenizer.model from Nanbeige/Nanbeige4.3-33B-Base: direct link, hf CLI and curl.
- Browser
- Download file 2.78 MB
-
https://huggingface.co/Nanbeige/Nanbeige4.3-33B-Base/resolve/main/tokenizer.model
- Command line
-
hf download hf://Nanbeige/Nanbeige4.3-33B-Base/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/Nanbeige/Nanbeige4.3-33B-Base/resolve/main/tokenizer.model
2.78 MB
- Xet hash:
- bacc5b30be0cd45a00b977ed564771cbee21d8b4176790f0854f62834b7ff203
- Size of remote file:
- 2.78 MB
- SHA256:
- fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.