Instructions to use IFM/K2-Horizon-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/K2-Horizon-32B with Transformers:

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

pipe = pipeline("text-generation", model="IFM/K2-Horizon-32B", 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-32B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IFM/K2-Horizon-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/K2-Horizon-32B"
# 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-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IFM/K2-Horizon-32B

SGLang

How to use IFM/K2-Horizon-32B 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-32B" \
    --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-32B",
		"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-32B" \
        --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-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/K2-Horizon-32B with Docker Model Runner:
```
docker model run hf.co/IFM/K2-Horizon-32B
```

K2-Horizon-32B

Commit History

Fix typo

99ffbe5
verified

desaifan-mbzuai commited on about 17 hours ago

Add Training Overview, Release Artifacts and Checkpoint Inventory sections to model card

0ef337d
verified

desaifan-mbzuai commited on about 18 hours ago

Document tool_call_format API options (#2)

36503b2

hunterhector

hanseungwook commited on 5 days ago

Model card: tip wording

466db5f
verified

hongli-zhan commited on 9 days ago

Model card: remove intro note

7897121
verified

hongli-zhan commited on 9 days ago

Model card: trim benchmark section text

05ff1db
verified

hongli-zhan commited on 9 days ago

Model card: larger caption

a14d24f
verified

hongli-zhan commited on 9 days ago

Model card: caption link as HTML

a842fcb
verified

hongli-zhan commited on 9 days ago

Model card: larger table caption

b06318c
verified

hongli-zhan commited on 9 days ago

Model card: remove APPENDIX.md

a9803d7
verified

hongli-zhan commited on 9 days ago

Model card: remove appendix references

f4c9aa4
verified

hongli-zhan commited on 9 days ago

Model card: SGLang line wording

335a9bb
verified

hongli-zhan commited on 9 days ago

Model card: vLLM line punctuation

e3121cd
verified

hongli-zhan commited on 9 days ago

Model card: drop revisions bullet

3e4fe58
verified

hongli-zhan commited on 9 days ago

Model card: drop output-length bullet

9317f9d
verified

hongli-zhan commited on 9 days ago

Model card: reasoning effort wording

eac104c
verified

hongli-zhan commited on 9 days ago

Model card: vLLM line wording

bd196a1
verified

hongli-zhan commited on 9 days ago

Model card: vLLM recipe link

6fa1b46
verified

hongli-zhan commited on 9 days ago

Model card: SGLang cookbook link

60db011
verified

hongli-zhan commited on 9 days ago

Model card: chart legend label, no footnote, larger axis labels

7da0dad
verified

hongli-zhan commited on 9 days ago

Model card: move release note into intro

7ced256
verified

hongli-zhan commited on 10 days ago

Model card: note wording

447d3ce
verified

hongli-zhan commited on 10 days ago

Model card: release note at top

2e58643
verified

hongli-zhan commited on 10 days ago

Model card: rename to K2-Horizon-32B-Stage1

77bb6dc
verified

hongli-zhan commited on 10 days ago

Model card: stage note in highlights

79903e1
verified

hongli-zhan commited on 10 days ago

Model card: remove Model Overview

9214649
verified

hongli-zhan commited on 10 days ago

Model card: bullet title

2aa3566
verified

hongli-zhan commited on 10 days ago

Model card: move Model Overview after Benchmark Results

5bf34d1
verified

hongli-zhan commited on 10 days ago

Model card: fully open wording

b0e76d9
verified

hongli-zhan commited on 10 days ago

Model card: staged checkpoints wording

c3d1671
verified

hongli-zhan commited on 10 days ago

Model card: highlights wording

bec7463
verified

hongli-zhan commited on 10 days ago

Model card: remove link bar

a909dcb
verified

hongli-zhan commited on 10 days ago

Model card: benchmark chart, results table, technical appendix

8395542
verified

hongli-zhan commited on 10 days ago

Updated K2-Horizon-MoVA-36B-A4B

a3c84c2
verified

aaryamonvikram commited on 10 days ago

docs: update SGLang quickstart (#1)

abac703