Instructions to use moonshotai/Kimi-K2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-K2.5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K2.5", trust_remote_code=True)
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, AutoModel

processor = AutoProcessor.from_pretrained("moonshotai/Kimi-K2.5", trust_remote_code=True)
model = AutoModel.from_pretrained("moonshotai/Kimi-K2.5", trust_remote_code=True, 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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-K2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-K2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moonshotai/Kimi-K2.5",
		"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/moonshotai/Kimi-K2.5

SGLang

How to use moonshotai/Kimi-K2.5 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 "moonshotai/Kimi-K2.5" \
    --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": "moonshotai/Kimi-K2.5",
		"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 "moonshotai/Kimi-K2.5" \
        --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": "moonshotai/Kimi-K2.5",
		"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 moonshotai/Kimi-K2.5 with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-K2.5
```

bigeagle

TomGrc commited on Jan 28

Commit

8d93622

verified ·

1 Parent(s): 911dce1

Fix grammar and punctuation errors in README.md (#12)

Browse files

- Fix grammar and punctuation errors in README.md (58556c39bc3ac04f8b8a9f2b50099e6bc5a99a10)

Co-authored-by: Suqin Zhang <TomGrc@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -529,7 +529,7 @@ Kimi-K2.5 adopts the same native int4 quantization method as [Kimi-K2-Thinking](
 ## 5. Deployment
 > [!Note]
-> You can access Kimi-K2.5's API on https://platform.moonshot.ai , we provide OpenAI/Anthropic-compatible API for you. To verify the deployment is correct, we also provide the  [Kimi Vendor Verifier](https://kimi.com/blog/kimi-vendor-verifier.html).
 Currently, Kimi-K2.5 is recommended to run on the following inference engines:
 * vLLM
 * SGLang
@@ -545,13 +545,13 @@ Deployment examples can be found in the [Model Deployment Guide](docs/deploy_gui
 The usage demos below demonstrate how to call our official API.
-For third-party API deployed with vLLM or SGLang, please note that :
 > [!Note]
-> - Chat with video content is an experimental feature and is only supported in our official API for now
 >
 > - The recommended `temperature` will be `1.0` for Thinking mode and `0.6` for Instant mode.
 >
-> - The recommended `top_p` is `0.95`
 >
 > - To use instant mode, you need to pass `{'chat_template_kwargs': {"thinking": False}}` in `extra_body`.
@@ -576,9 +576,9 @@ def simple_chat(client: openai.OpenAI, model_name: str):
     response = client.chat.completions.create(
         model=model_name, messages=messages, stream=False, max_tokens=4096
     )
-    print('===== Below is reasoning_content in Thinking Mode ======')
     print(f'reasoning content: {response.choices[0].message.reasoning_content}')
-    print('===== Below is response in Thinking Mode ======')
     print(f'response: {response.choices[0].message.content}')
     # To use instant mode, pass {"thinking" = {"type":"disabled"}}
@@ -590,7 +590,7 @@ def simple_chat(client: openai.OpenAI, model_name: str):
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
-    print('===== Below is response in Instant Mode ======')
     print(f'response: {response.choices[0].message.content}')
 ```
@@ -625,12 +625,12 @@ def chat_with_image(client: openai.OpenAI, model_name: str):
     response = client.chat.completions.create(
         model=model_name, messages=messages, stream=False, max_tokens=8192
     )
-    print('===== Below is reasoning_content in Thinking Mode ======')
     print(f'reasoning content: {response.choices[0].message.reasoning_content}')
-    print('===== Below is response in Thinking Mode ======')
     print(f'response: {response.choices[0].message.content}')
-    # Also support instant mode if pass {"thinking" = {"type":"disabled"}}
     response = client.chat.completions.create(
         model=model_name,
         messages=messages,
@@ -639,7 +639,7 @@ def chat_with_image(client: openai.OpenAI, model_name: str):
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
-    print('===== Below is response in Instant Mode ======')
     print(f'response: {response.choices[0].message.content}')
     return response.choices[0].message.content
@@ -669,9 +669,9 @@ def chat_with_video(client: openai.OpenAI, model_name:str):
     ]
     response = client.chat.completions.create(model=model_name, messages=messages)
-    print('===== Below is reasoning_content in Thinking Mode ======')
     print(f'reasoning content: {response.choices[0].message.reasoning_content}')
-    print('===== Below is response in Thinking Mode ======')
     print(f'response: {response.choices[0].message.content}')
     # Also support instant mode if pass {"thinking" = {"type":"disabled"}}
@@ -683,7 +683,7 @@ def chat_with_video(client: openai.OpenAI, model_name:str):
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
-    print('===== Below is response in Instant Mode ======')
     print(f'response: {response.choices[0].message.content}')
     return response.choices[0].message.content
 ```

 ## 5. Deployment
 > [!Note]
+> You can access Kimi-K2.5's API on https://platform.moonshot.ai and we provide OpenAI/Anthropic-compatible API for you. To verify the deployment is correct, we also provide the  [Kimi Vendor Verifier](https://kimi.com/blog/kimi-vendor-verifier.html).
 Currently, Kimi-K2.5 is recommended to run on the following inference engines:
 * vLLM
 * SGLang
 The usage demos below demonstrate how to call our official API.
+For third-party APIs deployed with vLLM or SGLang, please note that:
 > [!Note]
+> - Chat with video content is an experimental feature and is only supported in our official API for now.
 >
 > - The recommended `temperature` will be `1.0` for Thinking mode and `0.6` for Instant mode.
 >
+> - The recommended `top_p` is `0.95`.
 >
 > - To use instant mode, you need to pass `{'chat_template_kwargs': {"thinking": False}}` in `extra_body`.
     response = client.chat.completions.create(
         model=model_name, messages=messages, stream=False, max_tokens=4096
     )
+    print('====== Below is reasoning_content in Thinking Mode ======')
     print(f'reasoning content: {response.choices[0].message.reasoning_content}')
+    print('====== Below is response in Thinking Mode ======')
     print(f'response: {response.choices[0].message.content}')
     # To use instant mode, pass {"thinking" = {"type":"disabled"}}
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
+    print('====== Below is response in Instant Mode ======')
     print(f'response: {response.choices[0].message.content}')
 ```
     response = client.chat.completions.create(
         model=model_name, messages=messages, stream=False, max_tokens=8192
     )
+    print('====== Below is reasoning_content in Thinking Mode ======')
     print(f'reasoning content: {response.choices[0].message.reasoning_content}')
+    print('====== Below is response in Thinking Mode ======')
     print(f'response: {response.choices[0].message.content}')
+    # Also support instant mode if you pass {"thinking" = {"type":"disabled"}}
     response = client.chat.completions.create(
         model=model_name,
         messages=messages,
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
+    print('====== Below is response in Instant Mode ======')
     print(f'response: {response.choices[0].message.content}')
     return response.choices[0].message.content
     ]
     response = client.chat.completions.create(model=model_name, messages=messages)
+    print('====== Below is reasoning_content in Thinking Mode ======')
     print(f'reasoning content: {response.choices[0].message.reasoning_content}')
+    print('====== Below is response in Thinking Mode ======')
     print(f'response: {response.choices[0].message.content}')
     # Also support instant mode if pass {"thinking" = {"type":"disabled"}}
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
+    print('====== Below is response in Instant Mode ======')
     print(f'response: {response.choices[0].message.content}')
     return response.choices[0].message.content
 ```