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)
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
```

AttributeError: 'CompressedLinear' object has no attribute 'weight'

#39

by xbeark - opened Feb 3

Discussion

xbeark

Feb 3

•

edited Feb 3

When I try to load model with transformers

Traceback (most recent call last):
File "/home/ccc/nas/try_kimi-with-transformers/V2/load.py", line 415, in
main()
File "/home/ccc/nas/try_kimi-with-transformers/V2/load.py", line 403, in main
result = compute_refusal_directions(config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ccc/nas/try_kimi-with-transformers/V2/load.py", line 66, in compute_refusal_directions
model = AutoModelForCausalLM.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 365, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4110, in from_pretrained
load_info = cls._finalize_load_state_dict(model, load_config, load_info)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4274, in _finalize_load_state_dict
model._initialize_missing_keys(load_config.is_quantized)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4550, in _initialize_missing_keys
self.initialize_weights()
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/try_kimi/lib/python3.11/contextlib.py", line 81, in inner
return func(*args, **kwds)
^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2373, in initialize_weights
self.smart_apply(self._initialize_weights)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2364, in smart_apply
module.smart_apply(module._initialize_weights)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2364, in smart_apply
module.smart_apply(module._initialize_weights)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2366, in smart_apply
module.smart_apply(fn)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2366, in smart_apply
module.smart_apply(fn)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2366, in smart_apply
module.smart_apply(fn)
[Previous line repeated 3 more times]
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2367, in smart_apply
fn(self)
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2344, in _initialize_weights
self._init_weights(module)
File "/root/.cache/huggingface/modules/transformers_modules/moonshotai/Kimi_hyphen_K2_dot_5/c415995b2384f8927990eaf8454c8a0e0f3f2549/modeling_deepseek.py", line 1248, in init_weights
module.weight.data.normal(mean=0.0, std=std)
^^^^^^^^^^^^^
File "/root/miniconda3/envs/try_kimi/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1965, in getattr
raise AttributeError(
AttributeError: 'CompressedLinear' object has no attribute 'weight'

fxmarty-amd

Mar 26

Same issue

bigmoyan

Moonshot AI org Apr 29

please refer to discussion in https://huggingface.co/moonshotai/Kimi-K2.6/discussions/22

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment