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
```

zhou94539 commited on 4 days ago

Commit

f9a6f62

verified ·

1 Parent(s): 83a96fe

Upload migration_manifest.json to rl-mopd

Browse files

Files changed (1) hide show

migration_manifest.json +40 -0

migration_manifest.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "aurora_commit": "e47c5555caa987ded29dba0624d3de1b34cf6162",
+  "aurora_repo": "/mnt/weka/home/mrunner/workspace/code/eval360-v2/runtime/eval-runtime/releases/20260825T235203Z-e47c5555caa9-646960/repo/vendor/xllm-dataloader1",
+  "completed_utc": "2026-09-02T21:20:07Z",
+  "converter": "/mnt/weka/home/mrunner/workspace/code/tools/conversion_aurora2horizon/convert_k2aurora_to_k2horizon.py",
+  "horizon_commit": "42ae4f88016b083a8f514655d93521d6af006de9",
+  "horizon_repo": "/mnt/weka/home/mrunner/workspace/code/eval360-v2/runtime/eval-runtime/releases/20260825T235203Z-e47c5555caa9-646960/repo/vendor/xllm-dataloader1-horizon",
+  "output_checkpoint": "/mnt/weka/home/mrunner/workspace/checkpoints/k2horizon_bf16_safetensors/xllm_mopd_v1_a10b05_3t_mathcode_stem_if_train500_lr1e7_opd01_refkl001_v1/checkpoints/checkpoint_0000249",
+  "schema_version": 1,
+  "source_checkpoint": "/mnt/weka/shrd/k2m/junlin.chen/xllm_1b_final/model",
+  "source_hashes": {
+    "config.json": "f0ebfa59d5569edf77de34e32739b43978a8f1da355fefd825d6ed6284143870",
+    "configuration_k2_aurora.py": "90efba266ef94d3959e7f490e56146da48225e4539cca87ed6fcfea77872ce6d",
+    "model.safetensors.index.json": "5652ee0f725133f74a7a2cfb2673845230cf89cfc7d480cd64b90211db53e19e",
+    "modeling_k2_aurora.py": "aa6e3ea27c90eca3a88b7fcfaa0aa5235c6ac22e45e33ea4f0a613dc07821924"
+  },
+  "source_model_type": "k2_aurora",
+  "target_hashes": {
+    "config.json": "0ba8f6a0fe8daa5003f88c335735cabc7dba20600ace939efab949ae5e59b936",
+    "configuration_k2_horizon.py": "5c2f993c1053d9462ebea6dea416c897fddfbb4a5edd904e486936b20d4badc5",
+    "model.safetensors.index.json": "5652ee0f725133f74a7a2cfb2673845230cf89cfc7d480cd64b90211db53e19e",
+    "modeling_k2_horizon.py": "fb09e010956bd51cfa7d4055b4381cff34c9e06164066b49e3546f38b2e6242f"
+  },
+  "target_model_type": "k2_horizon",
+  "weight_mode": "copy",
+  "weights": {
+    "dtypes": [
+      "BF16"
+    ],
+    "filenames": [
+      "model-00000-of-00001.safetensors"
+    ],
+    "index_sha256": "5652ee0f725133f74a7a2cfb2673845230cf89cfc7d480cd64b90211db53e19e",
+    "logical_bytes": 2156571648,
+    "physical_bytes": 2156600968,
+    "shards": 1,
+    "tensors": 255
+  },
+  "weights_reencoded": false
+}