Instructions to use KSKOOO/HakuChat-Code-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KSKOOO/HakuChat-Code-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="KSKOOO/HakuChat-Code-9B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("KSKOOO/HakuChat-Code-9B")
model = AutoModelForMultimodalLM.from_pretrained("KSKOOO/HakuChat-Code-9B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KSKOOO/HakuChat-Code-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KSKOOO/HakuChat-Code-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KSKOOO/HakuChat-Code-9B",
		"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/KSKOOO/HakuChat-Code-9B

SGLang

How to use KSKOOO/HakuChat-Code-9B 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 "KSKOOO/HakuChat-Code-9B" \
    --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": "KSKOOO/HakuChat-Code-9B",
		"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 "KSKOOO/HakuChat-Code-9B" \
        --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": "KSKOOO/HakuChat-Code-9B",
		"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 KSKOOO/HakuChat-Code-9B with Docker Model Runner:
```
docker model run hf.co/KSKOOO/HakuChat-Code-9B
```

KSKOOO commited on 3 days ago

Commit

f46f2fb

verified ·

1 Parent(s): 4b3e9f3

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +19 -2

README.md CHANGED Viewed

@@ -18,11 +18,28 @@ HakuChat 是一个本地部署的中文代码助手，本仓库为 9B 参数全
 - Python 代码生成、补全、函数实现与解释
 - 工具调用（calculator / web.search 轨迹）
 - 长上下文：原生支持 256k，部署配置 128k
-## 评测
-见仓库 `eval_results.json`（MMLU / C-Eval / CMMLU / GSM8K / HumanEval）。
 ```
 对话模板内置身份设定，调用时无需额外 system prompt。

 - Python 代码生成、补全、函数实现与解释
 - 工具调用（calculator / web.search 轨迹）
 - 长上下文：原生支持 256k，部署配置 128k
+- 中文对话与身份统一为 HakuChat
+## 评测结果（线上 int4 / 128k，temperature=0）
+| Benchmark | 分数 | 样本数 |
+|---|---|---|
+| MMLU | 73.1 | 171 |
+| C-Eval | 78.85 | 104 |
+| GSM8K | 86.67 | 60 |
+| HumanEval (pass@1) | 63.33 | 60 |
+口径说明：0-shot 生成式采样，采样数见上表；同类模型多为厂商 5-shot/bf16 成绩，数值仅供量级参考。
+## 使用
+```python
+from transformers import AutoModelForImageTextToText, AutoTokenizer
+tok = AutoTokenizer.from_pretrained("KSKOOO/HakuChat-Code-9B")
+model = AutoModelForImageTextToText.from_pretrained(
+    "KSKOOO/HakuChat-Code-9B", dtype="auto", device_map="auto")
 ```
 对话模板内置身份设定，调用时无需额外 system prompt。