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

Libraries

How to use tencent/Hy3-preview with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/Hy3-preview")
model = AutoModelForCausalLM.from_pretrained("tencent/Hy3-preview")
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 with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

SaylorTwift HF Staff commited on Apr 23

Commit

b9fee63

verified ·

1 Parent(s): ab24fda

Add evaluation results: HLE, GPQA Diamond, SWE-bench Verified, Terminal-Bench 2.0

Browse files

Files changed (4) hide show

.eval_results/gpqa.yaml +9 -0
.eval_results/hle.yaml +9 -0
.eval_results/swe_bench_verified.yaml +9 -0
.eval_results/terminal_bench.yaml +9 -0

.eval_results/gpqa.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 87.2
+  date: '2026-04-14'
+  source:
+    url: https://huggingface.co/tencent/Hy3-preview
+    name: Model Card

.eval_results/hle.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 30.0
+  date: '2026-04-14'
+  source:
+    url: https://huggingface.co/tencent/Hy3-preview
+    name: Model Card
+  notes: "Text-only"

.eval_results/swe_bench_verified.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 74.4
+  date: '2026-04-14'
+  source:
+    url: https://huggingface.co/tencent/Hy3-preview
+    name: Model Card

.eval_results/terminal_bench.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: harborframework/terminal-bench-2.0
+    task_id: terminalbench_2
+  value: 54.4
+  date: '2026-04-14'
+  source:
+    url: https://huggingface.co/tencent/Hy3-preview
+    name: Model Card