Instructions to use IFM/K2-Think-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IFM/K2-Think-V2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IFM/K2-Think-V2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IFM/K2-Think-V2") model = AutoModelForCausalLM.from_pretrained("IFM/K2-Think-V2", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IFM/K2-Think-V2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IFM/K2-Think-V2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IFM/K2-Think-V2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/IFM/K2-Think-V2
- SGLang
How to use IFM/K2-Think-V2 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 "IFM/K2-Think-V2" \ --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": "IFM/K2-Think-V2", "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 "IFM/K2-Think-V2" \ --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": "IFM/K2-Think-V2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use IFM/K2-Think-V2 with Docker Model Runner:
docker model run hf.co/IFM/K2-Think-V2
File size: 6,707 Bytes
041bdeb 258698f 041bdeb | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | {%- if tools %}
{{- "<|im_start|>system\n" }}
{%- if messages[0].role == 'system' and messages[0].content %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "\n# Tools\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- if messages[0].get('tools') %}
{%- if messages[0].content %}
{{- '<|im_start|>system\n' + messages[0].content + '\n\n' }}
{%- else %}
{{- '<|im_start|>system\n\n' }}
{%- endif %}
{{- "# Tools\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in messages[0]['tools'] %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set thinking_content = '' %}
{%- set think_tag = '' %}
{%- if message.think is defined and message.think is string %}
{%- set thinking_content = message.think %}
{%- set think_tag = 'think' %}
{%- elif message.think_fast is defined and message.think_fast is string %}
{%- set thinking_content = message.think_fast %}
{%- set think_tag = 'think_fast' %}
{%- elif message.think_faster is defined and message.think_faster is string %}
{%- set thinking_content = message.think_faster %}
{%- set think_tag = 'think_faster' %}
{%- else %}
{%- if '</think>' in content %}
{%- set thinking_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- set think_tag = 'think' %}
{%- elif '</think_fast>' in content %}
{%- set thinking_content = content.split('</think_fast>')[0].rstrip('\n').split('<think_fast>')[-1].lstrip('\n') %}
{%- set content = content.split('</think_fast>')[-1].lstrip('\n') %}
{%- set think_tag = 'think_fast' %}
{%- elif '</think_faster>' in content %}
{%- set thinking_content = content.split('</think_faster>')[0].rstrip('\n').split('<think_faster>')[-1].lstrip('\n') %}
{%- set content = content.split('</think_faster>')[-1].lstrip('\n') %}
{%- set think_tag = 'think_faster' %}
{%- else %}
{%- set thinking_content = '' %}
{%- set think_tag = 'think_faster' %}
{%- endif %}
{%- endif %}
{{- '<|im_start|>' + message.role }}
{% generation %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last and think_tag %}
{%- if thinking_content %}
{{- '<' + think_tag + '>\n' + thinking_content + '\n</' + think_tag + '>\n' + content.lstrip('\n') }}
{%- else %}
{{- '<' + think_tag + '>\n</' + think_tag + '>\n' + content.lstrip('\n') }}
{%- endif %}
{%- else %}
{{- content }}
{%- endif %}
{%- else %}
{{- content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>' }}
{% endgeneration %}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>tool\n' }}
{%- endif %}
{{- content }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{%- set effort = reasoning_effort | default('high') %}
{%- if effort == 'high' %}
{{- '<|im_start|>assistant\n<think>\n' }}
{%- elif effort == 'medium' %}
{{- '<|im_start|>assistant\n<think_fast>\n' }}
{%- elif effort == 'low' %}
{{- '<|im_start|>assistant\n<think_faster>\n' }}
{%- else %}
{{- '<|im_start|>assistant\n<think>\n' }}
{%- endif %}
{%- endif %}
|