Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
text-generation-inference
Instructions to use tiny-random/kimi-k2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiny-random/kimi-k2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tiny-random/kimi-k2", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tiny-random/kimi-k2", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("tiny-random/kimi-k2", trust_remote_code=True) 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use tiny-random/kimi-k2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tiny-random/kimi-k2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tiny-random/kimi-k2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/tiny-random/kimi-k2
- SGLang
How to use tiny-random/kimi-k2 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 "tiny-random/kimi-k2" \ --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": "tiny-random/kimi-k2", "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 "tiny-random/kimi-k2" \ --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": "tiny-random/kimi-k2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use tiny-random/kimi-k2 with Docker Model Runner:
docker model run hf.co/tiny-random/kimi-k2
| { | |
| "added_tokens_decoder": { | |
| "163584": { | |
| "content": "[BOS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163585": { | |
| "content": "[EOS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163586": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163587": { | |
| "content": "<|im_user|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163588": { | |
| "content": "<|im_assistant|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163590": { | |
| "content": "<|start_header_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163591": { | |
| "content": "<|end_header_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163593": { | |
| "content": "[EOT]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163594": { | |
| "content": "<|im_system|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163595": { | |
| "content": "<|tool_calls_section_begin|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "163596": { | |
| "content": "<|tool_calls_section_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "163597": { | |
| "content": "<|tool_call_begin|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "163598": { | |
| "content": "<|tool_call_argument_begin|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "163599": { | |
| "content": "<|tool_call_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "163601": { | |
| "content": "<|im_middle|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163838": { | |
| "content": "[UNK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163839": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|im_end|>", | |
| "<|im_user|>", | |
| "<|im_assistant|>", | |
| "<|start_header_id|>", | |
| "<|end_header_id|>", | |
| "[EOT]", | |
| "<|im_system|>", | |
| "<|im_middle|>" | |
| ], | |
| "bos_token": "[BOS]", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "[EOS]", | |
| "extra_special_tokens": {}, | |
| "chat_template": "{%- if tools -%}\n <|im_system|>tool_declare<|im_middle|>{{ tools | tojson }}<|im_end|>\n{%- endif -%}\n{%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>\n {%- endif -%}\n {%- if message['role'] == 'system' -%}\n <|im_system|>system<|im_middle|>\n {%- elif message['role'] == 'user' -%}\n <|im_user|>user<|im_middle|>\n {%- elif message['role'] == 'assistant' -%}\n <|im_assistant|>assistant<|im_middle|>\n {%- elif message['role'] == 'tool' -%}\n <|im_system|>tool<|im_middle|>\n {%- endif -%}\n {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}\n {%- if message['content'] -%}{{ message['content'] }}{%- endif -%}\n <|tool_calls_section_begin|>\n {%- for tool_call in message['tool_calls'] -%}\n {%- set formatted_id = tool_call['id'] -%}\n <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>\n {%- endfor -%}\n <|tool_calls_section_end|>\n {%- elif message['role'] == 'tool' -%}\n ## Return of {{ message.tool_call_id }}\n {{ message['content'] }}\n {%- elif message['content'] is string -%}\n {{ message['content'] }}\n {%- elif message['content'] is not none -%}\n {% for content in message['content'] -%}\n {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n <|media_start|>image<|media_content|><|media_pad|><|media_end|>\n {% else -%}\n {{ content['text'] }}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n <|im_end|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|im_assistant|>assistant<|im_middle|>\n{%- endif -%}", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "tokenizer_class": "TikTokenTokenizer", | |
| "unk_token": "[UNK]", | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "moonshotai/Kimi-K2-Instruct--tokenization_kimi.TikTokenTokenizer", | |
| null | |
| ] | |
| } | |
| } |