Instructions to use tencent/Hy3-preview-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hy3-preview-Base with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hy3-preview-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/Hy3-preview-Base")
model = AutoModelForCausalLM.from_pretrained("tencent/Hy3-preview-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tencent/Hy3-preview-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hy3-preview-Base"
# 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/Hy3-preview-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hy3-preview-Base

SGLang

How to use tencent/Hy3-preview-Base 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/Hy3-preview-Base" \
    --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/Hy3-preview-Base",
		"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/Hy3-preview-Base" \
        --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/Hy3-preview-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hy3-preview-Base with Docker Model Runner:
```
docker model run hf.co/tencent/Hy3-preview-Base
```

Hy3-preview-Base / config.json

yiqichen01

Add files using upload-large-folder tool

f71230b verified 16 days ago

raw

history blame

1.06 kB

	{
	"architectures": [
	"HYV3ForCausalLM"
	],
	"enable_attention_fp32_softmax": false,
	"enable_lm_head_fp32": true,
	"enable_moe_fp32_combine": false,
	"expert_hidden_dim": 1536,
	"moe_intermediate_size": 1536,
	"first_k_dense_replace": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.006,
	"intermediate_size": 13312,
	"max_position_embeddings": 262144,
	"model_type": "hy_v3",
	"moe_router_enable_expert_bias": true,
	"moe_router_use_sigmoid": true,
	"num_attention_heads": 64,
	"num_experts": 192,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 80,
	"num_key_value_heads": 8,
	"num_shared_experts": 1,
	"output_router_logits": true,
	"qk_norm": true,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 11158840.0,
	"rope_type": "default"
	},
	"route_norm": true,
	"router_scaling_factor": 2.826,
	"tie_word_embeddings": false,
	"transformers_version": "5.6.0",
	"use_cache": true,
	"use_grouped_mm": false,
	"vocab_size": 120832,
	"num_nextn_predict_layers": 1
	}