Instructions to use IFM/K2-Horizon-0.9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/K2-Horizon-0.9B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="IFM/K2-Horizon-0.9B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IFM/K2-Horizon-0.9B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IFM/K2-Horizon-0.9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/K2-Horizon-0.9B"
# 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-Horizon-0.9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IFM/K2-Horizon-0.9B

SGLang

How to use IFM/K2-Horizon-0.9B 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-Horizon-0.9B" \
    --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-Horizon-0.9B",
		"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-Horizon-0.9B" \
        --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-Horizon-0.9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/K2-Horizon-0.9B with Docker Model Runner:
```
docker model run hf.co/IFM/K2-Horizon-0.9B
```

K2-Horizon-0.9B / ifm_tokenizer_manifest.json

zhou94539

Upload ifm_tokenizer_manifest.json to rl-mopd

83a96fe verified 4 days ago

Raw

History Blame Contribute Delete

1.95 kB

	{
	"source_tokenizer": "/lustrefs/users/junlin.chen/data/tokenizers/jais64k_bbq_chat_nonspecial_toolthink",
	"source_template": "/lustrefs/users/bbqbyte/workspace/code/bbq-chat-template/bbq-0610",
	"token_id_replacements": {
	"64018": {
	"content": "<\|ifm\|im_start\|>",
	"special": true
	},
	"64019": {
	"content": "<\|ifm\|im_end\|>",
	"special": true
	},
	"64029": {
	"content": "<ifm\|think>",
	"special": false
	},
	"64030": {
	"content": "</ifm\|think>",
	"special": false
	},
	"64041": {
	"content": "<ifm\|tools>",
	"special": false
	},
	"64042": {
	"content": "</ifm\|tools>",
	"special": false
	},
	"64043": {
	"content": "<ifm\|tool_call>",
	"special": false
	},
	"64044": {
	"content": "</ifm\|tool_call>",
	"special": false
	},
	"64050": {
	"content": "<ifm\|think_fast>",
	"special": false
	},
	"64051": {
	"content": "</ifm\|think_fast>",
	"special": false
	},
	"64052": {
	"content": "<ifm\|think_faster>",
	"special": false
	},
	"64053": {
	"content": "</ifm\|think_faster>",
	"special": false
	},
	"64054": {
	"content": "<ifm\|tool_calls>",
	"special": false
	},
	"64055": {
	"content": "</ifm\|tool_calls>",
	"special": false
	},
	"64056": {
	"content": "<ifm\|arg_key>",
	"special": false
	},
	"64057": {
	"content": "</ifm\|arg_key>",
	"special": false
	},
	"64058": {
	"content": "<ifm\|arg_type>",
	"special": false
	},
	"64059": {
	"content": "</ifm\|arg_type>",
	"special": false
	},
	"64060": {
	"content": "<ifm\|arg_value>",
	"special": false
	},
	"64061": {
	"content": "</ifm\|arg_value>",
	"special": false
	}
	},
	"tool_presentation_format": "markdown",
	"tool_call_format": "xml",
	"vocab_size_unchanged": true
	}