qwen3.6-35b-moe-kuato-base

Instructions to use lxz8798/qwen3.6-35b-moe-kuato-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lxz8798/qwen3.6-35b-moe-kuato-base with Transformers:

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

pipe = pipeline("image-text-to-text", model="lxz8798/qwen3.6-35b-moe-kuato-base")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lxz8798/qwen3.6-35b-moe-kuato-base")
model = AutoModelForMultimodalLM.from_pretrained("lxz8798/qwen3.6-35b-moe-kuato-base", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lxz8798/qwen3.6-35b-moe-kuato-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lxz8798/qwen3.6-35b-moe-kuato-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": "lxz8798/qwen3.6-35b-moe-kuato-base",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lxz8798/qwen3.6-35b-moe-kuato-base

SGLang

How to use lxz8798/qwen3.6-35b-moe-kuato-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 "lxz8798/qwen3.6-35b-moe-kuato-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": "lxz8798/qwen3.6-35b-moe-kuato-base",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "lxz8798/qwen3.6-35b-moe-kuato-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": "lxz8798/qwen3.6-35b-moe-kuato-base",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use lxz8798/qwen3.6-35b-moe-kuato-base with Docker Model Runner:
```
docker model run hf.co/lxz8798/qwen3.6-35b-moe-kuato-base
```

lxz8798 commited on Jun 16

Commit

5b71e1d

verified ·

1 Parent(s): cfae321

Update handler.py

Browse files

Files changed (1) hide show

handler.py +16 -1

handler.py CHANGED Viewed

@@ -1,9 +1,24 @@
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 class EndpointHandler:
     def __init__(self, path=""):
-        # 1. 强制使用 trust_remote_code=True 加载 Tokenizer 和 Model
         self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
         self.model = AutoModelForCausalLM.from_pretrained(
             path,

+import subprocess
+import sys
+# 🚀 强制在代码运行最开始，从 PyPI 热升级 transformers 和 accelerate 到最新版本
+try:
+    print("Starting hot-upgrade of transformers and accelerate...")
+    subprocess.run(
+        [sys.executable, "-m", "pip", "install", "--upgrade", "transformers", "accelerate", "--user"],
+        check=True
+    )
+    print("Hot-upgrade completed successfully!")
+except Exception as e:
+    print(f"Warning during hot-upgrade: {e}")
+# ----------------- 升级完成后再导入库 -----------------
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 class EndpointHandler:
     def __init__(self, path=""):
+        # 1. 使用 trust_remote_code=True 加载 Tokenizer 和 Model
         self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
         self.model = AutoModelForCausalLM.from_pretrained(
             path,