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

Commit History

docs: update SGLang quickstart (#1)

070513c

akhauriyash commited on 14 days ago

Upload validation.json to rl-mopd

d9eb85d
verified

zhou94539 commited on 14 days ago

Upload tokenizer_config.json to rl-mopd

4801b68
verified

zhou94539 commited on 14 days ago

Upload tokenizer.json to rl-mopd

48db50d
verified

zhou94539 commited on 14 days ago

Upload special_tokens_map.json to rl-mopd

021b8ae
verified

zhou94539 commited on 14 days ago

Upload modeling_k2_horizon.py to rl-mopd

7066b76
verified

zhou94539 commited on 14 days ago

Upload model.safetensors.index.json to rl-mopd

4a8f62a
verified

zhou94539 commited on 14 days ago

Upload model-00000-of-00001.safetensors to rl-mopd

ce6e7e0
verified

zhou94539 commited on 14 days ago

Upload migration_manifest.json to rl-mopd

f9a6f62
verified

zhou94539 commited on 14 days ago

Upload ifm_tokenizer_manifest.json to rl-mopd

83a96fe
verified

zhou94539 commited on 14 days ago

Upload generation_config.json to rl-mopd

f4593a8
verified

zhou94539 commited on 14 days ago

Upload configuration_k2_horizon.py to rl-mopd

d4d5372
verified

zhou94539 commited on 14 days ago

Upload config.json to rl-mopd

aa164f1
verified

zhou94539 commited on 14 days ago

Upload chat_template_generation.jinja to rl-mopd

9ddd29a
verified

zhou94539 commited on 14 days ago

Upload chat_template_asst_tool_gen.jinja to rl-mopd

b3dd072
verified

zhou94539 commited on 14 days ago

Upload chat_template.jinja to rl-mopd

921922f
verified

zhou94539 commited on 14 days ago

Initialize private staging repo

140df16
verified

zhou94539 commited on 15 days ago

initial commit

b09d727
verified

zhou94539 commited on 15 days ago

Commit History

docs: update SGLang quickstart (#1) 070513c

Upload validation.json to rl-mopd d9eb85d verified

Upload tokenizer_config.json to rl-mopd 4801b68 verified

Upload tokenizer.json to rl-mopd 48db50d verified

Upload special_tokens_map.json to rl-mopd 021b8ae verified

Upload modeling_k2_horizon.py to rl-mopd 7066b76 verified

Upload model.safetensors.index.json to rl-mopd 4a8f62a verified

Upload model-00000-of-00001.safetensors to rl-mopd ce6e7e0 verified

Upload migration_manifest.json to rl-mopd f9a6f62 verified

Upload ifm_tokenizer_manifest.json to rl-mopd 83a96fe verified

Upload generation_config.json to rl-mopd f4593a8 verified

Upload configuration_k2_horizon.py to rl-mopd d4d5372 verified

Upload config.json to rl-mopd aa164f1 verified

Upload chat_template_generation.jinja to rl-mopd 9ddd29a verified

Upload chat_template_asst_tool_gen.jinja to rl-mopd b3dd072 verified

Upload chat_template.jinja to rl-mopd 921922f verified

Initialize private staging repo 140df16 verified

initial commit b09d727 verified

docs: update SGLang quickstart (#1)

070513c

Upload validation.json to rl-mopd

d9eb85d
verified

Upload tokenizer_config.json to rl-mopd

4801b68
verified

Upload tokenizer.json to rl-mopd

48db50d
verified

Upload special_tokens_map.json to rl-mopd

021b8ae
verified

Upload modeling_k2_horizon.py to rl-mopd

7066b76
verified

Upload model.safetensors.index.json to rl-mopd

4a8f62a
verified

Upload model-00000-of-00001.safetensors to rl-mopd

ce6e7e0
verified

Upload migration_manifest.json to rl-mopd

f9a6f62
verified

Upload ifm_tokenizer_manifest.json to rl-mopd

83a96fe
verified

Upload generation_config.json to rl-mopd

f4593a8
verified

Upload configuration_k2_horizon.py to rl-mopd

d4d5372
verified

Upload config.json to rl-mopd

aa164f1
verified

Upload chat_template_generation.jinja to rl-mopd

9ddd29a
verified

Upload chat_template_asst_tool_gen.jinja to rl-mopd

b3dd072
verified

Upload chat_template.jinja to rl-mopd

921922f
verified

Initialize private staging repo

140df16
verified

initial commit

b09d727
verified