Text Generation
Transformers
Safetensors
deepseek_v3
unsloth
conversational
custom_code
text-generation-inference
fp8
Instructions to use unsloth/Kimi-K2-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use unsloth/Kimi-K2-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="unsloth/Kimi-K2-Instruct", 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("unsloth/Kimi-K2-Instruct", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("unsloth/Kimi-K2-Instruct", 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 unsloth/Kimi-K2-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "unsloth/Kimi-K2-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "unsloth/Kimi-K2-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/unsloth/Kimi-K2-Instruct
- SGLang
How to use unsloth/Kimi-K2-Instruct 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 "unsloth/Kimi-K2-Instruct" \ --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": "unsloth/Kimi-K2-Instruct", "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 "unsloth/Kimi-K2-Instruct" \ --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": "unsloth/Kimi-K2-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use unsloth/Kimi-K2-Instruct with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for unsloth/Kimi-K2-Instruct to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for unsloth/Kimi-K2-Instruct to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for unsloth/Kimi-K2-Instruct to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="unsloth/Kimi-K2-Instruct", max_seq_length=2048, ) - Docker Model Runner
How to use unsloth/Kimi-K2-Instruct with Docker Model Runner:
docker model run hf.co/unsloth/Kimi-K2-Instruct
Upload folder using huggingface_hub
Browse files- chat_template.jinja +43 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools -%}
|
| 2 |
+
<|im_system|>tool_declare<|im_middle|>{{ tools | tojson }}<|im_end|>
|
| 3 |
+
{%- endif -%}
|
| 4 |
+
{%- for message in messages -%}
|
| 5 |
+
{%- if loop.first and messages[0]['role'] != 'system' -%}
|
| 6 |
+
<|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
|
| 7 |
+
{%- endif -%}
|
| 8 |
+
{%- if message['role'] == 'system' -%}
|
| 9 |
+
<|im_system|>system<|im_middle|>
|
| 10 |
+
{%- elif message['role'] == 'user' -%}
|
| 11 |
+
<|im_user|>user<|im_middle|>
|
| 12 |
+
{%- elif message['role'] == 'assistant' -%}
|
| 13 |
+
<|im_assistant|>assistant<|im_middle|>
|
| 14 |
+
{%- elif message['role'] == 'tool' -%}
|
| 15 |
+
<|im_system|>tool<|im_middle|>
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- if message['role'] == 'assistant' and message.get('tool_calls') -%}
|
| 18 |
+
{%- if message['content'] -%}{{ message['content'] }}{%- endif -%}
|
| 19 |
+
<|tool_calls_section_begin|>
|
| 20 |
+
{%- for tool_call in message['tool_calls'] -%}
|
| 21 |
+
{%- set formatted_id = tool_call['id'] -%}
|
| 22 |
+
<|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|>
|
| 23 |
+
{%- endfor -%}
|
| 24 |
+
<|tool_calls_section_end|>
|
| 25 |
+
{%- elif message['role'] == 'tool' -%}
|
| 26 |
+
## Return of {{ message.tool_call_id }}
|
| 27 |
+
{{ message['content'] }}
|
| 28 |
+
{%- elif message['content'] is string -%}
|
| 29 |
+
{{ message['content'] }}
|
| 30 |
+
{%- elif message['content'] is not none -%}
|
| 31 |
+
{% for content in message['content'] -%}
|
| 32 |
+
{% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
|
| 33 |
+
<|media_start|>image<|media_content|><|media_pad|><|media_end|>
|
| 34 |
+
{% else -%}
|
| 35 |
+
{{ content['text'] }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- endif -%}
|
| 39 |
+
<|im_end|>
|
| 40 |
+
{%- endfor -%}
|
| 41 |
+
{%- if add_generation_prompt -%}
|
| 42 |
+
<|im_assistant|>assistant<|im_middle|>
|
| 43 |
+
{%- endif -%}
|