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 / config.json

zhou94539

Upload config.json to mid_5

4f44b4d verified 5 days ago

Raw

History Blame

1.98 kB

	{
	"architectures": [
	"K2HorizonForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_gate_func": null,
	"auto_map": {
	"AutoConfig": "configuration_k2_horizon.K2HorizonConfig",
	"AutoModel": "modeling_k2_horizon.K2HorizonModel",
	"AutoModelForCausalLM": "modeling_k2_horizon.K2HorizonForCausalLM"
	},
	"bos_token_id": 0,
	"decoder_sparse_step": 1,
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"intermediate_size": 26624,
	"layernorm_num_groups": 4,
	"max_position_embeddings": 524288,
	"mlp_only_layers": [
	0,
	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
	],
	"model_type": "k2_horizon",
	"moe_gate_bias": false,
	"moe_intermediate_size": 0,
	"mova_num_experts": 0,
	"mova_num_experts_per_tok": 0,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts": 0,
	"num_experts_per_tok": 0,
	"num_hidden_layers": 64,
	"num_key_value_heads": 8,
	"num_shared_experts": 0,
	"output_router_logits": false,
	"pad_token_id": null,
	"query_key_norm": false,
	"rms_norm_eps": 1e-06,
	"rope_head_dim": 128,
	"rope_parameters": {
	"rope_theta": 10000000.0,
	"rope_type": "default"
	},
	"router_aux_loss_coef": 0.001,
	"router_scaling_factor": 1.0,
	"router_score_func": "sigmoid",
	"sliding_window": null,
	"tie_word_embeddings": false,
	"transformers_version": "5.13.0",
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 250624
	}