Instructions to use tencent/Hy4-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hy4-preview with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hy4-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tencent/Hy4-preview", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tencent/Hy4-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hy4-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Hy4-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hy4-preview

SGLang

How to use tencent/Hy4-preview 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 "tencent/Hy4-preview" \
    --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": "tencent/Hy4-preview",
		"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 "tencent/Hy4-preview" \
        --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": "tencent/Hy4-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hy4-preview with Docker Model Runner:
```
docker model run hf.co/tencent/Hy4-preview
```

Hy4-preview / config.json

yiqichen01

Update transformers_version to 5.16.2

5a05584 verified 2 days ago

Raw

History Blame Contribute Delete

6.32 kB

	{
	"architectures": [
	"HYV4ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bitwise_backward_align": false,
	"bos_token_id": 120000,
	"dtype": "bfloat16",
	"enable_ihc": true,
	"enable_lm_head_fp32": true,
	"eos_token_id": 120025,
	"gated_mla": true,
	"gating_type": "elementwise",
	"hc_eps": 1e-06,
	"hc_magnitude": 2.0,
	"hc_mult": 4,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 6144,
	"index_head_dim": 128,
	"index_n_heads": 32,
	"index_topk": 2048,
	"indexer_types": [
	"full",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full",
	"shared",
	"shared",
	"shared",
	"full"
	],
	"initializer_range": 0.006,
	"intermediate_size": 18432,
	"kv_lora_rank": 512,
	"layer_types": [
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention",
	"deepseek_sparse_attention"
	],
	"learnable_sink": true,
	"learnable_sink_init": 0.0,
	"max_position_embeddings": 1048576,
	"mlp_layer_types": [
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "hy_v4",
	"moe_intermediate_size": 2048,
	"mtp_loss_factor": 0.1,
	"n_group": 1,
	"n_routed_experts": 256,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 78,
	"num_key_value_heads": 8,
	"num_nextn_predict_layers": 1,
	"pad_token_id": 120002,
	"q_lora_rank": 2048,
	"qk_head_dim": 256,
	"qk_nope_head_dim": 192,
	"qk_rope_head_dim": 64,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"routed_scaling_factor": 2.827,
	"swiglu_limit": 10.0,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"transformers_version": "5.16.2",
	"use_cache": true,
	"use_dsa": true,
	"use_mla": true,
	"v_head_dim": 256,
	"vocab_size": 120832,
	"torch_dtype": "bfloat16"
	}