Text Generation
Transformers
Safetensors
GGUF
English
lfm2
kailu
kvchub
small-language-model
conversational
Instructions to use KvcHub/KaiLu-3-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KvcHub/KaiLu-3-Pro with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="KvcHub/KaiLu-3-Pro") 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("KvcHub/KaiLu-3-Pro") model = AutoModelForCausalLM.from_pretrained("KvcHub/KaiLu-3-Pro", 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
- llama.cpp
How to use KvcHub/KaiLu-3-Pro with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf KvcHub/KaiLu-3-Pro:Q8_0 # Run inference directly in the terminal: llama cli -hf KvcHub/KaiLu-3-Pro:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf KvcHub/KaiLu-3-Pro:Q8_0 # Run inference directly in the terminal: llama cli -hf KvcHub/KaiLu-3-Pro:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf KvcHub/KaiLu-3-Pro:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf KvcHub/KaiLu-3-Pro:Q8_0
Use Docker
docker model run hf.co/KvcHub/KaiLu-3-Pro:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use KvcHub/KaiLu-3-Pro with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "KvcHub/KaiLu-3-Pro" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KvcHub/KaiLu-3-Pro", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/KvcHub/KaiLu-3-Pro:Q8_0
- SGLang
How to use KvcHub/KaiLu-3-Pro 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 "KvcHub/KaiLu-3-Pro" \ --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": "KvcHub/KaiLu-3-Pro", "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 "KvcHub/KaiLu-3-Pro" \ --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": "KvcHub/KaiLu-3-Pro", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use KvcHub/KaiLu-3-Pro with Ollama:
ollama run hf.co/KvcHub/KaiLu-3-Pro:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use KvcHub/KaiLu-3-Pro with Docker Model Runner:
docker model run hf.co/KvcHub/KaiLu-3-Pro:Q8_0
- Lemonade
How to use KvcHub/KaiLu-3-Pro with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull KvcHub/KaiLu-3-Pro:Q8_0
Run and chat with the model
lemonade run user.KaiLu-3-Pro-Q8_0
List all available models
lemonade list
- Atomic Chat
Download tokenizer_config.json from KvcHub/KaiLu-3-Pro: direct link, hf CLI and curl.
- Browser
- Download file 946 Bytes
-
https://huggingface.co/KvcHub/KaiLu-3-Pro/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://KvcHub/KaiLu-3-Pro/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/KvcHub/KaiLu-3-Pro/resolve/main/tokenizer_config.json
946 Bytes
| { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|endoftext|>", | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 1024, | |
| "pad_token": "<|endoftext|>", | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "chat_template": "{%- set roles = {'system': 'system', 'user': 'user', 'human': 'user', 'assistant': 'assistant', 'gpt': 'assistant'} -%}{%- if not messages or roles.get((messages[0]['role'] | string) | lower) != 'system' -%}{{- '<|system|>\\nYou are KaiLu, a helpful assistant.\\n' -}}{%- endif -%}{%- for message in messages -%}{%- set role = roles.get((message['role'] | string) | lower) -%}{%- if role -%}{{- '<|' + role + '|>\\n' + ((message['content'] or '') | string | trim) -}}{%- if role == 'assistant' -%}{{- '<|endoftext|>' -}}{%- endif -%}{{- '\\n' -}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '<|assistant|>\\n' -}}{%- endif -%}" | |
| } | |